<p>I don't know what is going on here but I'd bet that any index would be against the ibv_devices list.</p>
<div class="gmail_quote">On Sep 17, 2012 7:26 PM, "Todd Wilde" <<a href="mailto:Todd@mellanox.com">Todd@mellanox.com</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Ira,<br>
<br>
There may be bug here. I've always used '-i mlx4_0' in the past and it works.<br>
<br>
-Todd<br>
<br>
> -----Original Message-----<br>
> From: Ira Weiny [mailto:<a href="mailto:weiny2@llnl.gov">weiny2@llnl.gov</a>]<br>
> Sent: Monday, September 17, 2012 4:04 PM<br>
> To: Todd Wilde<br>
> Cc: <a href="mailto:users@lists.openfabrics.org">users@lists.openfabrics.org</a><br>
> Subject: Re: [Users] Another ibdiagnet question...<br>
><br>
> On Mon, 17 Sep 2012 22:40:13 +0000<br>
> Todd Wilde <Todd@Mellanox.com> wrote:<br>
><br>
> > Hi Ira,<br>
> ><br>
> > Try 'ibdiagnet -i mlx4_0 -p 2'<br>
> ><br>
> > -Todd<br>
><br>
> I tried that:<br>
><br>
> bash-4.1# ibdiagnet -i mlx4_0 -p 2<br>
> Loading IBDIAGNET from: /usr/lib64/ibdiagnet1.5.7<br>
><br>
> -E- Illegal argument: Illegal value for -i option: mlx4_0<br>
> (Legal value: a positive integer number).<br>
> Exiting.<br>
><br>
> SYNOPSYS<br>
> ibdiagnet [-c <count>] [-v] [-r] [-u] [-o <out-dir>]<br>
> [-t <topo-file>] [-s <sys-name>] [-i <dev-index>] [-p <port-num>] [-wt]<br>
> [-pm] [-pc] [-P <<PM>=<Value>>]<br>
> [-lw <1x|4x|12x>] [-ls <2.5|5|10>]<br>
> [-skip <ibdiag check>] [-load_db <db_file>] [-csv] [-vlr]<br>
><br>
> This is with the RHEL 6 ibutils.<br>
><br>
> bash-4.1# rpm -qf `which ibdiagnet`<br>
> ibutils-1.5.7-6.el6.x86_64<br>
><br>
> Perhaps there is a bug?<br>
><br>
> Ira<br>
><br>
> ><br>
> ><br>
> ><br>
> > > -----Original Message-----<br>
> > > From: <a href="mailto:users-bounces@lists.openfabrics.org">users-bounces@lists.openfabrics.org</a> [mailto:<a href="mailto:users-">users-</a><br>
> > > <a href="mailto:bounces@lists.openfabrics.org">bounces@lists.openfabrics.org</a>] On Behalf Of Ira Weiny<br>
> > > Sent: Monday, September 17, 2012 3:36 PM<br>
> > > To: <a href="mailto:users@lists.openfabrics.org">users@lists.openfabrics.org</a><br>
> > > Subject: [Users] Another ibdiagnet question...<br>
> > ><br>
> > ><br>
> > > Does anyone understand the "-i <dev-index>" option?<br>
> > ><br>
> > > I have a system with 3 cards in it like this (summary from ibstat)[*]:<br>
> > ><br>
> > > mlx4_0 (IB)<br>
> > > port 1: down<br>
> > > port 2: up<br>
> > > mlx4_1 (Eth)<br>
> > > port 1: up<br>
> > > port 2: down<br>
> > > qib0 (IB)<br>
> > > port 1: up<br>
> > ><br>
> > > The "-i" option to ibdiagnet wants (from the man page):<br>
> > ><br>
> > > "the index of the device of the port used to connect to the IB<br>
> > > fabric (in case of multiple devices on the local system)"<br>
> > ><br>
> > > I don't quite understand what that means. I _thought_ it would mean<br>
> > > that<br>
> > > mlx4_0 == 1, mlx4_1 == 2, qib0 ==3.<br>
> > ><br>
> > > so I tried:<br>
> > ><br>
> > > bash-4.1# ibdiagnet -i 1 -p 2<br>
> > > Loading IBDIAGNET from: /usr/lib64/ibdiagnet1.5.7<br>
> > > -W- Topology file is not specified.<br>
> > > Reports regarding cluster links will use direct routes.<br>
> > > Loading IBDM from: /usr/lib64/ibdm1.5.7<br>
> > ><br>
> > > -E- Device number: 1 does not have port number: 2.<br>
> > > Exiting.<br>
> > ><br>
> > ><br>
> > > So perhaps it is zero based?<br>
> > ><br>
> > > bash-4.1# ibdiagnet -i 0 -p 2<br>
> > > Loading IBDIAGNET from: /usr/lib64/ibdiagnet1.5.7<br>
> > ><br>
> > > -E- Illegal argument: Illegal value for -i option: 0<br>
> > > (Legal value: a positive integer number).<br>
> > > Exiting.<br>
> > ><br>
> > > SYNOPSYS<br>
> > > ibdiagnet [-c <count>] [-v] [-r] [-u] [-o <out-dir>]<br>
> > > [-t <topo-file>] [-s <sys-name>] [-i <dev-index>] [-p <port-num>] [-<br>
> wt]<br>
> > > [-pm] [-pc] [-P <<PM>=<Value>>]<br>
> > > [-lw <1x|4x|12x>] [-ls <2.5|5|10>]<br>
> > > [-skip <ibdiag check>] [-load_db <db_file>] [-csv] [-vlr]<br>
> > ><br>
> > > Nope... What am I missing?<br>
> > ><br>
> > > Ira<br>
> > ><br>
> > ><br>
> > > [*] full output from ibstat:<br>
> > ><br>
> > > bash-4.1# ibstat<br>
> > > CA 'mlx4_0'<br>
> > > CA type: MT26428<br>
> > > Number of ports: 2<br>
> > > Firmware version: 2.8.600<br>
> > > Hardware version: b0<br>
> > > Node GUID: 0x0002c903004bebda<br>
> > > System image GUID: 0x0002c903004bebdd<br>
> > > Port 1:<br>
> > > State: Down<br>
> > > Physical state: Polling<br>
> > > Rate: 68<br>
> > > Base lid: 0<br>
> > > LMC: 0<br>
> > > SM lid: 0<br>
> > > Capability mask: 0x02510868<br>
> > > Port GUID: 0x0002c903004bebdb<br>
> > > Link layer: InfiniBand<br>
> > > Port 2:<br>
> > > State: Active<br>
> > > Physical state: LinkUp<br>
> > > Rate: 40<br>
> > > Base lid: 2<br>
> > > LMC: 0<br>
> > > SM lid: 1<br>
> > > Capability mask: 0x02510868<br>
> > > Port GUID: 0x0002c903004bebdc<br>
> > > Link layer: InfiniBand CA 'mlx4_1'<br>
> > > CA type: MT26448<br>
> > > Number of ports: 2<br>
> > > Firmware version: 2.7.0<br>
> > > Hardware version: a0<br>
> > > Node GUID: 0xffffffffffffffff<br>
> > > System image GUID: 0xffffffffffffffff<br>
> > > Port 1:<br>
> > > State: Active<br>
> > > Physical state: LinkUp<br>
> > > Rate: 10<br>
> > > Base lid: 0<br>
> > > LMC: 0<br>
> > > SM lid: 0<br>
> > > Capability mask: 0x00010000<br>
> > > Port GUID: 0x0202c9fffe02c593<br>
> > > Link layer: Ethernet<br>
> > > Port 2:<br>
> > > State: Down<br>
> > > Physical state: Disabled<br>
> > > Rate: 10<br>
> > > Base lid: 0<br>
> > > LMC: 0<br>
> > > SM lid: 0<br>
> > > Capability mask: 0x00010000<br>
> > > Port GUID: 0x0202c9fffe02c594<br>
> > > Link layer: Ethernet CA 'qib0'<br>
> > > CA type: InfiniPath_QLE7340<br>
> > > Number of ports: 1<br>
> > > Firmware version:<br>
> > > Hardware version: 1<br>
> > > Node GUID: 0x001175000079da38<br>
> > > System image GUID: 0x001175000079da38<br>
> > > Port 1:<br>
> > > State: Active<br>
> > > Physical state: LinkUp<br>
> > > Rate: 20<br>
> > > Base lid: 1<br>
> > > LMC: 0<br>
> > > SM lid: 1<br>
> > > Capability mask: 0x0761086a<br>
> > > Port GUID: 0x001175000079da38<br>
> > > Link layer: InfiniBand<br>
> > ><br>
> > ><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>
><br>
> --<br>
> Ira Weiny<br>
> Member of Technical Staff<br>
> Lawrence Livermore National Lab<br>
> <a href="tel:925-423-8008" value="+19254238008">925-423-8008</a><br>
> <a href="mailto:weiny2@llnl.gov">weiny2@llnl.gov</a><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>
</blockquote></div>