<!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: IBDM and IBMgtSim Proposal Comments</TITLE>
</HEAD>
<BODY>
<P><FONT SIZE=2>Hi Hal,</FONT>
</P>
<P><FONT SIZE=2>> Where does that leave the OpenIB diagnostics and other applications</FONT>
<BR><FONT SIZE=2>> which do not use this layer ? Does the simulator support these</FONT>
<BR><FONT SIZE=2>> applications ?</FONT>
<BR><FONT SIZE=2>[EZ] The simulator is a separate process that is a TCP/IP server.</FONT>
<BR><FONT SIZE=2>Any application that will send and receive simulator messages (as defined by simmsg.h) can connect to it. </FONT>
<BR><FONT SIZE=2>The osmv_sim (osm vendor layer for simulator) is just an example for such client.</FONT>
<BR><FONT SIZE=2>But one can even write perl or TCL applications that will connect. </FONT>
<BR><FONT SIZE=2>Actually the simulator provides a library named ibmscli that provides all the required TCP/IP (client/server) logic and exposes a simple API for such client.</FONT></P>
<P><FONT SIZE=2>Please see ibms_client_api.h for this API definition. </FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> In the OpenIB architecture, umad is the lowest layer library and the</FONT>
<BR><FONT SIZE=2>> diagnostics are built on that. The OSM vendor layer is built on top of</FONT>
<BR><FONT SIZE=2>> this. So when the umad and mad libraries are ported to Windows,</FONT>
<BR><FONT SIZE=2>> everything on top of this will work. This includes all diagnostics</FONT>
<BR><FONT SIZE=2>> (OpenIB ones as well as the additional tools you are proposing to add).</FONT>
<BR><FONT SIZE=2>[EZ] There is no need to port UMAD to windows!!! We already have OSM Vendor ported to it. It works on top of the existing IBAL API (actually this is the first OSM Vendor that was ever built).</FONT></P>
<P><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> Also, it appears that the Mellanox simulator is builtin to each</FONT>
<BR><FONT SIZE=2>> simulated process and so each instance is separate which limits its</FONT>
<BR><FONT SIZE=2>> usability.</FONT>
<BR><FONT SIZE=2>[EZ] This is totally incorrect - as explained before. We were able to simulate OpenSM, osmtest and IBIS (IB Inband Services - which is a simple API for sending MADs) all connected and communicating over the simulator. We were also able to simulate multiple SM's handoff processes. Where did you get this idea from?</FONT></P>
<P><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> In the Voltaire architecture proposed to be moved forward to OpenIB, the</FONT>
<BR><FONT SIZE=2>> simulator is standalone and hence is useable by all applications in the</FONT>
<BR><FONT SIZE=2>> network which can be on different nodes (TCP connections): OpenSM (as</FONT>
<BR><FONT SIZE=2>> many as you want in the subnet), diagnostics, SA clients, etc. Also, the</FONT>
<BR><FONT SIZE=2>> Voltaire simulator architecture can use an input file recorded from a</FONT>
<BR><FONT SIZE=2>> real IB fabric where it appears that this would be manual in the</FONT>
<BR><FONT SIZE=2>> Mellanox scheme.</FONT>
<BR><FONT SIZE=2>[EZ] The Voltaire simulator was never made public and actually has no benefit over what is provided by the IBMgtSim. </FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> The file formats (netlist and topology) are for further study. There are</FONT>
<BR><FONT SIZE=2>> some good ideas in these file formats which would be incorporated into</FONT>
<BR><FONT SIZE=2>> the ibnetdiscover format.</FONT>
<BR><FONT SIZE=2>[EZ] Thanks.</FONT>
<BR><FONT SIZE=2>> </FONT>
<BR><FONT SIZE=2>> -- Hal</FONT>
</P>
</BODY>
</HTML>