<!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: IB Diagnositic Tools</TITLE>
</HEAD>
<BODY>
<P><FONT SIZE=2>Hi Hal,</FONT>
</P>
<P><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Is the OpenSM vendor layer available in Windows for OpenIB or is this</FONT>
<BR><FONT SIZE=2>> something which needs to be developed ?</FONT>
<BR><FONT SIZE=2>[EZ] It is available (the code was part of IBAL but needed some fixes etc).</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> > Since this layer is already available on both Windows and Linux stacks</FONT>
<BR><FONT SIZE=2>> > it could allow us to have the same code tree for both.</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Will the Linux distros take it this way (with #ifdef OS)</FONT>
<BR><FONT SIZE=2>[EZ] The different implementations are already included in the OpenSM code on the OpenIB trunk. They are not named Win/Linux but IBAL, TS. I propose we perform some restructuring where each "vendor" has its own package and all of them are actually made into the same "lib" name. Such that for OpenSM build it should not make any difference which vendor it is linked with. </FONT></P>
<P><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Not sure exactly what you have in mind here but there is something like</FONT>
<BR><FONT SIZE=2>> this on the TODO list. How are GUIDs and LIDs aggregated into a name ?</FONT>
<BR><FONT SIZE=2>> Is this SystemImageGUID ?</FONT>
<BR><FONT SIZE=2>[EZ] I mean using topology file to map discovered topology to specified topology and thus enable the use of the user given names for the various systems (instead of guids).</FONT></P>
<P><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Not sure what you mean exactly by MAD and topology manipulations layers.</FONT>
<BR><FONT SIZE=2>> Are there different tools ? What do they provide different from the</FONT>
<BR><FONT SIZE=2>> current OpenIB diagnostics ?</FONT>
<BR><FONT SIZE=2>[EZ] The MAD layer provides scripting interface for sending receiving mads of the various classes. </FONT>
<BR><FONT SIZE=2>The analysis layers perform topology matching, LFT traversals, credit loop analysis, MFT connectivity checks, routing hops histograms, etc.</FONT></P>
<P><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> > If there is an interest in these tools we can provide an open version</FONT>
<BR><FONT SIZE=2>> > of those in week or two.</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Will the development then be done in the OpenIB tree or will the drop</FONT>
<BR><FONT SIZE=2>> model be used ? On the Linux side, the community desires the tools to be</FONT>
<BR><FONT SIZE=2>> built with autotools.</FONT>
<BR><FONT SIZE=2>[EZ] The idea is to move the current tools into OpenIB and use OpenIB as the development environment. This includes OpenSM and the MAD layers.</FONT></P>
<P><FONT SIZE=2>All should be autotools.</FONT>
</P>
</BODY>
</HTML>