<br><font size=2 face="sans-serif">The HCA is Mellanox MHES18-XSC.</font>
<br>
<br><font size=2 face="sans-serif">Thanks!</font>
<br><font size=2 face="sans-serif">Yicheng Jia<br>
<br>
</font>
<br>
<br>
<br>
<table width=100%>
<tr valign=top>
<td width=40%><font size=1 face="sans-serif"><b>Hal Rosenstock <hal.rosenstock@gmail.com></b>
</font>
<p><font size=1 face="sans-serif">04/16/2009 06:12 PM</font>
<td width=59%>
<table width=100%>
<tr valign=top>
<td>
<div align=right><font size=1 face="sans-serif">To</font></div>
<td><font size=1 face="sans-serif">Yicheng Jia <YJia@tmriusa.com></font>
<tr valign=top>
<td>
<div align=right><font size=1 face="sans-serif">cc</font></div>
<td><font size=1 face="sans-serif">Nicolas Morey-Chaisemartin <devel-ofed@morey-chaisemartin.com>,
general@lists.openfabrics.org</font>
<tr valign=top>
<td>
<div align=right><font size=1 face="sans-serif">Subject</font></div>
<td><font size=1 face="sans-serif">Re: [ofa-general] link width problem
of Qlogic 9024 unmanaged switch</font></table>
<br>
<table>
<tr valign=top>
<td>
<td></table>
<br></table>
<br>
<br>
<br><tt><font size=2>On Thu, Apr 16, 2009 at 6:06 PM, Yicheng Jia <YJia@tmriusa.com>
wrote:<br>
><br>
>> There's a race condition here that I was asking about. If the
link<br>
>> initialization takes too long and doesn't complete (gets to init)<br>
>> prior to the enable trying to be sent to the switch, then you
could<br>
>> see these results but since it's DOWN until reboot it's something<br>
>> different.<br>
><br>
> I did the "reset" when ports on both side of the link are
in INIT state and<br>
> LinkUp phys state.<br>
><br>
>> If the disable/wait/enable worked that would've been another story.<br>
><br>
> It fails too. Both ports go to DOWN after disable is issued and never
come<br>
> back. How long am I supposed to wait?<br>
<br>
Ideally you would see init before doing the enable but sounds like<br>
that's not occuring. Either you need low level debug to see why the<br>
link does not initialize at that point or get support from your<br>
CA/switch vendor(s). What's your CA device ?<br>
<br>
-- Hal<br>
<br>
> Thanks!<br>
> Yicheng Jia<br>
><br>
><br>
><br>
><br>
> Hal Rosenstock <hal.rosenstock@gmail.com><br>
><br>
> 04/16/2009 03:26 PM<br>
><br>
> To<br>
> Yicheng Jia <YJia@tmriusa.com><br>
> cc<br>
> Nicolas Morey-Chaisemartin <devel-ofed@morey-chaisemartin.com>,<br>
> general@lists.openfabrics.org<br>
> Subject<br>
> Re: [ofa-general] link width problem of Qlogic 9024 unmanaged switch<br>
><br>
><br>
><br>
><br>
> On Thu, Apr 16, 2009 at 3:47 PM, Yicheng Jia <YJia@tmriusa.com>
wrote:<br>
>><br>
>>> Are you resetting the switch from the peer HCA port or some
other port<br>
>>> ? That's what Nicolas asked but I might have missed the answer.<br>
>><br>
>> Yes, I am trying to reset from the peer HCA port. Is anything
wrong with<br>
>> this?<br>
><br>
> There's a race condition here that I was asking about. If the link<br>
> initialization takes too long and doesn't complete (gets to init)<br>
> prior to the enable trying to be sent to the switch, then you could<br>
> see these results but since it's DOWN until reboot it's something<br>
> different.<br>
><br>
>>> Also, try disable (wait) and then enable and see if that works.<br>
>><br>
>> It remains the same, the switch port is DOWN forever. No SMP massage
could<br>
>> get to the switch port.<br>
><br>
> Right; in down, the SMP can't be sent.<br>
><br>
>>> If I recall correctly, you had those links which are taking
a long time<br>
>>> to<br>
>>> initialize. If the link stays down forever after disable,
this won't<br>
>>> work but I want to be sure.<br>
>><br>
>> This is seperate issue.<br>
><br>
> Since the link stays down yes. If the disable/wait/enable worked that<br>
> would've been another story.<br>
><br>
> -- Hal<br>
><br>
>> The "reset" command is tested on a single port HCA<br>
>> directly connected with Qlogic siwth. The HCA is plugged into
a Linux<br>
>> machine. It is the simplest test environment.<br>
>><br>
>> Thanks!<br>
>> Yicheng Jia<br>
>><br>
>><br>
>><br>
>><br>
>> Hal Rosenstock <hal.rosenstock@gmail.com><br>
>><br>
>> 04/16/2009 02:29 PM<br>
>><br>
>> To<br>
>> Yicheng Jia <YJia@tmriusa.com><br>
>> cc<br>
>> Nicolas Morey-Chaisemartin <devel-ofed@morey-chaisemartin.com>,<br>
>> general@lists.openfabrics.org<br>
>> Subject<br>
>> Re: [ofa-general] link width problem of Qlogic 9024 unmanaged
switch<br>
>><br>
>><br>
>><br>
>><br>
>> On Thu, Apr 16, 2009 at 3:20 PM, Hal Rosenstock<br>
>> <hal.rosenstock@gmail.com> wrote:<br>
>>> On Thu, Apr 16, 2009 at 3:18 PM, Yicheng Jia <YJia@tmriusa.com>
wrote:<br>
>>>><br>
>>>> They both are POLLING before "reset".<br>
>>><br>
>>> Then they _should_ come back to INIT.<br>
>>><br>
>>> What does the local LDDS value say after reset ? Any way to
get the<br>
>>> switch port LDDS value ?<br>
>><br>
>> Are you resetting the switch from the peer HCA port or some other
port<br>
>> ? That's what Nicolas asked but I might have missed the answer.<br>
>><br>
>> Also, try disable (wait) and then enable and see if that works.
If I<br>
>> recall correctly, you had those links which are taking a long
time to<br>
>> initialize. If the link stays down forever after disable, this
won't<br>
>> work but I want to be sure.<br>
>><br>
>> -- Hal<br>
>><br>
>>> -- Hal<br>
>>><br>
>>>> Thanks!<br>
>>>> Yicheng Jia<br>
>>>><br>
>>>><br>
>>>><br>
>>>><br>
>>>> Hal Rosenstock <hal.rosenstock@gmail.com><br>
>>>><br>
>>>> 04/16/2009 01:53 PM<br>
>>>><br>
>>>> To<br>
>>>> Yicheng Jia <YJia@tmriusa.com><br>
>>>> cc<br>
>>>> Nicolas Morey-Chaisemartin <devel-ofed@morey-chaisemartin.com>,<br>
>>>> general@lists.openfabrics.org<br>
>>>> Subject<br>
>>>> Re: [ofa-general] link width problem of Qlogic 9024 unmanaged
switch<br>
>>>><br>
>>>><br>
>>>><br>
>>>><br>
>>>> On Thu, Apr 16, 2009 at 11:12 AM, Yicheng Jia <YJia@tmriusa.com>
wrote:<br>
>>>>><br>
>>>>> Hi Nicolas,<br>
>>>>><br>
>>>>> After this "reset" command, both ports are
DOWN forever, I can only get<br>
>>>>> portinfo from local port.<br>
>>>>><br>
>>>>> I am sure that the port that has been reset is not
the local port,<br>
>>>>> otherwise<br>
>>>>> it will prompt "node type not switch" error.<br>
>>>>><br>
>>>>> I tried to enable this switch port from another port
and brought it to<br>
>>>>> POLLING state, but as long as I use "reset",
both ports are DOWN.<br>
>>>><br>
>>>> What are the peer port's LinkDownDefaultStates ? Sounds
like one or<br>
>>>> more must be Sleeping rather than Polling for some reason.<br>
>>>><br>
>>>> -- Hal<br>
>>>><br>
>>>>> Thanks!<br>
>>>>><br>
>>>>> Yicheng Jia<br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>> Nicolas Morey-Chaisemartin <devel-ofed@morey-chaisemartin.com><br>
>>>>><br>
>>>>> 04/16/2009 12:43 AM<br>
>>>>><br>
>>>>> To<br>
>>>>> Yicheng Jia <YJia@tmriusa.com><br>
>>>>> cc<br>
>>>>> general@lists.openfabrics.org<br>
>>>>> Subject<br>
>>>>> Re: [ofa-general] link width problem of Qlogic 9024
unmanaged switch<br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>> By any chances have you not reset the port you're
on?<br>
>>>>> Have you tried using another node to enable the port
again?<br>
>>>>><br>
>>>>> Nicolas<br>
>>>>><br>
>>>>> Le 16/04/2009 00:45, Yicheng Jia a écrit :<br>
>>>>>><br>
>>>>>> Hello Randy,<br>
>>>>>><br>
>>>>>> I am trying to run "ibportstate reset"
to reset the switch port on the<br>
>>>>>> other side in order to get 4x link. However I
get the following error:<br>
>>>>>> ibwarn: [19660] mad_rpc: _do_madrpc failed; dport
(Lid 7)<br>
>>>>>> ibportstate: iberror: failed: smp set portinfo
failed<br>
>>>>>><br>
>>>>>> And the port status change to DOWN after this.
Have you ever tried to<br>
>>>>>> run "ibportstate" to reset the switch
port?<br>
>>>>>><br>
>>>>>> Thanks!<br>
>>>>>><br>
>>>>>> Yicheng Jia<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> ------------------------------<br>
>>>>>><br>
>>>>>> Message: 2<br>
>>>>>> Date: Wed, 4 Mar 2009 18:39:54 -0600<br>
>>>>>> From: Randy Halverson <randy.halverson@qlogic.com><br>
>>>>>> Subject: [ofa-general] link width problem of Qlogic
9024 unmanaged<br>
>>>>>> switch<br>
>>>>>> To: "'general@lists.openfabrics.org'"
<general@lists.openfabrics.org><br>
>>>>>> Message-ID:<br>
>>>>>> <88EC963376E93B4DB0F2A69D932F786903D89CAF@MNEXMB2.qlogic.org><br>
>>>>>> Content-Type: text/plain; charset="us-ascii"<br>
>>>>>><br>
>>>>>> Hello Yicheng,<br>
>>>>>><br>
>>>>>> After checking internally, this appears to be
a known problem with<br>
>>>>>> older<br>
>>>>>> firmware for the 9024FC switches.<br>
>>>>>><br>
>>>>>> It appears that you or another person at 'tmriusa.com'
has recently<br>
>>>>>> opened a case with QLogic Tech Support for this
issue. Please continue<br>
>>>>>> to work with QLogic Tech Support on firmware upgrade
resolution since<br>
>>>>>> you probably don't have our FastFabric Tools to
manage the 9024FC<br>
>>>>>> switches..<br>
>>>>>><br>
>>>>>> Regards,<br>
>>>>>><br>
>>>>>> Randy<br>
>>>>>> Technical Support<br>
>>>>>> QLogic Corporation<br>
>>>>>> -------------- next part --------------<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> _____________________________________________________________________________<br>
>>>>>> Scanned by IBM Email Security Management Services
powered by<br>
>>>>>> MessageLabs. For more information please visit
</font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> _____________________________________________________________________________<br>
>>>>>> <</font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com/><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> _____________________________________________________________________________<br>
>>>>>> Scanned by IBM Email Security Management Services
powered by<br>
>>>>>> MessageLabs. For more information please visit
</font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> _____________________________________________________________________________<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> ------------------------------------------------------------------------<br>
>>>>>><br>
>>>>>> _______________________________________________<br>
>>>>>> general mailing list<br>
>>>>>> general@lists.openfabrics.org<br>
>>>>>> </font></tt><a href="http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general"><tt><font size=2>http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general<br>
>>>>>><br>
>>>>>> To unsubscribe, please visit<br>
>>>>>> </font></tt><a href="http://openib.org/mailman/listinfo/openib-general"><tt><font size=2>http://openib.org/mailman/listinfo/openib-general<br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>> _____________________________________________________________________________<br>
>>>>> Scanned by IBM Email Security Management Services
powered by<br>
>>>>> MessageLabs.<br>
>>>>> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>> _____________________________________________________________________________<br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>> _____________________________________________________________________________<br>
>>>>> Scanned by IBM Email Security Management Services
powered by<br>
>>>>> MessageLabs.<br>
>>>>> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>> _____________________________________________________________________________<br>
>>>>><br>
>>>>> _______________________________________________<br>
>>>>> general mailing list<br>
>>>>> general@lists.openfabrics.org<br>
>>>>> </font></tt><a href="http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general"><tt><font size=2>http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general<br>
>>>>><br>
>>>>> To unsubscribe, please visit<br>
>>>>> </font></tt><a href="http://openib.org/mailman/listinfo/openib-general"><tt><font size=2>http://openib.org/mailman/listinfo/openib-general<br>
>>>>><br>
>>>><br>
>>>><br>
>>>><br>
>>>> _____________________________________________________________________________<br>
>>>> Scanned by IBM Email Security Management Services powered
by<br>
>>>> MessageLabs.<br>
>>>> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>>>><br>
>>>><br>
>>>> _____________________________________________________________________________<br>
>>>><br>
>>>><br>
>>>><br>
>>>><br>
>>>> _____________________________________________________________________________<br>
>>>> Scanned by IBM Email Security Management Services powered
by<br>
>>>> MessageLabs.<br>
>>>> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>>>><br>
>>>><br>
>>>> _____________________________________________________________________________<br>
>>>><br>
>>><br>
>><br>
>><br>
>> _____________________________________________________________________________<br>
>> Scanned by IBM Email Security Management Services powered by MessageLabs.<br>
>> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>><br>
>> _____________________________________________________________________________<br>
>><br>
>><br>
>><br>
>> _____________________________________________________________________________<br>
>> Scanned by IBM Email Security Management Services powered by MessageLabs.<br>
>> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
>><br>
>> _____________________________________________________________________________<br>
>><br>
><br>
> _____________________________________________________________________________<br>
> Scanned by IBM Email Security Management Services powered by MessageLabs.<br>
> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
> _____________________________________________________________________________<br>
><br>
><br>
> _____________________________________________________________________________<br>
> Scanned by IBM Email Security Management Services powered by MessageLabs.<br>
> For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
> _____________________________________________________________________________<br>
><br>
<br>
_____________________________________________________________________________<br>
Scanned by IBM Email Security Management Services powered by MessageLabs.
For more information please visit </font></tt><a href=http://www.ers.ibm.com/><tt><font size=2>http://www.ers.ibm.com<br>
_____________________________________________________________________________<br>
</font></tt></a></a></a></a></a></a></a></a></a></a></a></a></a></a></a></a>
<br>
<BR>
_____________________________________________________________________________<BR>
Scanned by IBM Email Security Management Services powered by MessageLabs. For more information please visit http://www.ers.ibm.com<BR>
_____________________________________________________________________________<BR>