<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii">
<META NAME="Generator" CONTENT="MS Exchange Server version 5.5.2654.45">
<TITLE>RE: [Openib-windows] Re: [openib-general] Re: IB Diagnositic Tools</TITLE>
</HEAD>
<BODY>
<P><FONT SIZE=2>Hi Ben</FONT>
</P>
<P><FONT SIZE=2>The patch try to start scanning the ports from i=1 rather then i=0.</FONT>
</P>
<P><FONT SIZE=2>status = osm_vendor_get_all_port_attr(p_osm->p_vendor, attr_array, &num_ports );</FONT>
</P>
<P><FONT SIZE=2>But this function to return the port attributes of all available ports does not use the "port number" as index into the returned array of port attributes. It simply starts with i=0 and adds on to it. The port numbers are available in the attributes struct.</FONT></P>
<P><FONT SIZE=2>Eitan Zahavi</FONT>
<BR><FONT SIZE=2>Design Technology Director</FONT>
<BR><FONT SIZE=2>Mellanox Technologies LTD</FONT>
<BR><FONT SIZE=2>Tel:+972-4-9097208</FONT>
<BR><FONT SIZE=2>Fax:+972-4-9593245</FONT>
<BR><FONT SIZE=2>P.O. Box 586 Yokneam 20692 ISRAEL</FONT>
</P>
<BR>
<P><FONT SIZE=2>> -----Original Message-----</FONT>
<BR><FONT SIZE=2>> From: Bernhard Fischer [<A HREF="mailto:rep.nop@aon.at">mailto:rep.nop@aon.at</A>]</FONT>
<BR><FONT SIZE=2>> Sent: Monday, July 04, 2005 11:44 PM</FONT>
<BR><FONT SIZE=2>> To: Hal Rosenstock</FONT>
<BR><FONT SIZE=2>> Cc: Bernhard Fischer; Eitan Zahavi; openib-windows@openib.org; 'openib-</FONT>
<BR><FONT SIZE=2>> general@openib.org'</FONT>
<BR><FONT SIZE=2>> Subject: Re: [Openib-windows] Re: [openib-general] Re: IB Diagnositic Tools</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> On Tue, Jun 28, 2005 at 09:22:00AM -0400, Hal Rosenstock wrote:</FONT>
<BR><FONT SIZE=2>> >On Mon, 2005-06-27 at 17:30, Hal Rosenstock wrote:</FONT>
<BR><FONT SIZE=2>> >> On Mon, 2005-06-27 at 17:13, Bernhard Fischer wrote:</FONT>
<BR><FONT SIZE=2>> >> > Hal,</FONT>
<BR><FONT SIZE=2>> >> ></FONT>
<BR><FONT SIZE=2>> >> > This is kinda offtopic,</FONT>
<BR><FONT SIZE=2>> >></FONT>
<BR><FONT SIZE=2>> >> Yes, this is different topic(s).</FONT>
<BR><FONT SIZE=2>> >></FONT>
<BR><FONT SIZE=2>> >> > but (iirc) i once stumbled over the issue of</FONT>
<BR><FONT SIZE=2>> >> > "port" vs. "mgmt port" [back then i had access to two 2-port cards]</FONT>
<BR><FONT SIZE=2>> >> > where you may have said something along the lines of</FONT>
<BR><FONT SIZE=2>> >> > \"There is clearly a bug for multi HCAs in osm_vendor_get_all_port_attr</FONT>
<BR><FONT SIZE=2>> >> > which is in the vendor layer. This needs to be fixed and is our problem.</FONT>
<BR><FONT SIZE=2>> >> > So I am close to being able to commit what I now have for this and fix</FONT>
<BR><FONT SIZE=2>> >> > this later (as there are other multi HCA issues).\"</FONT>
<BR><FONT SIZE=2>> >> > Just curious.. did somebody already have a chance to touch those or not?</FONT>
<BR><FONT SIZE=2>> >></FONT>
<BR><FONT SIZE=2>> >> I don't think it has been fixed :-( I will need to refresh myself on</FONT>
<BR><FONT SIZE=2>> >> this again.</FONT>
<BR><FONT SIZE=2>> ></FONT>
<BR><FONT SIZE=2>> >Just tried the diags and OpenSM on a multi HCA machine and they appear</FONT>
<BR><FONT SIZE=2>> >to run fine. I will need to dig out from my notes as that comment came</FONT>
<BR><FONT SIZE=2>> >from back on 2/16.</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Please note that that specific occurance was *not* triggered in a strict</FONT>
<BR><FONT SIZE=2>> \"multi HCA\" setup but with two-port HCA(s e.g. opensm'd) back-to_back.</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Back then, i saw (can't reproduce it now since i do not have access to</FONT>
<BR><FONT SIZE=2>> an appropriate setup; can't reproduce since even if i would have access</FONT>
<BR><FONT SIZE=2>> to such a setup i most likely wouldn't have root access) a listing akin</FONT>
<BR><FONT SIZE=2>> to :</FONT>
<BR><FONT SIZE=2>> phy-port 1</FONT>
<BR><FONT SIZE=2>> phy-port 1</FONT>
<BR><FONT SIZE=2>> phy-port 2</FONT>
<BR><FONT SIZE=2>> e-o-f</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Please mail me the output of</FONT>
<BR><FONT SIZE=2>> opensm -g</FONT>
<BR><FONT SIZE=2>> [with opensm as primary SM -- but i guess it does literally everywhere,</FONT>
<BR><FONT SIZE=2>> be it hosts or switches] with the attached patch.</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> PS: Hal, if the moved question is true, please point me to a document</FONT>
<BR><FONT SIZE=2>> and section where this is defined. I may be a pita, but i'd like to</FONT>
<BR><FONT SIZE=2>> know that answer. TIA and .....</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> ..sorry for the noise</FONT>
<BR><FONT SIZE=2>> --</FONT>
<BR><FONT SIZE=2>> Bernhard</FONT>
</P>
</BODY>
</HTML>