of
resolving this problem?
Thanks!
Yicheng Jia
Ira Weiny wei...@llnl.gov
04/17/2009 12:45 PM
To
Yicheng Jia y...@tmriusa.com
cc
general@lists.openfabrics.org, Hal Rosenstock hal.rosenst...@gmail.com
Subject
Re: ***SPAM*** Re: [ofa-general] link width problem of Qlogic 9024
unmanaged
it to
POLLING state, but as long as I use reset, both ports are DOWN.
Thanks!
Yicheng Jia
Nicolas Morey-Chaisemartin devel-o...@morey-chaisemartin.com
04/16/2009 12:43 AM
To
Yicheng Jia y...@tmriusa.com
cc
general@lists.openfabrics.org
Subject
Re: [ofa-general] link width problem of Qlogic
They both are POLLING before reset.
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
04/16/2009 01:53 PM
To
Yicheng Jia y...@tmriusa.com
cc
Nicolas Morey-Chaisemartin devel-o...@morey-chaisemartin.com,
general@lists.openfabrics.org
Subject
Re: [ofa-general] link width problem
Then they _should_ come back to INIT.
No, they don't.
What does the local LDDS value say after reset ? Any way to get the
switch port LDDS value ?
How can I check the LDDS value?
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
04/16/2009 02:21 PM
To
Yicheng Jia y...@tmriusa.com
command is tested on a single port HCA
directly connected with Qlogic siwth. The HCA is plugged into a Linux
machine. It is the simplest test environment.
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
04/16/2009 02:29 PM
To
Yicheng Jia y...@tmriusa.com
cc
Nicolas Morey
Thought you said they were both POLLING prior to reset.
Yes, they are. I don't know what LDDS stands for in the first place:)
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
04/16/2009 02:37 PM
To
Yicheng Jia y...@tmriusa.com
cc
Nicolas Morey-Chaisemartin devel-o...@morey
!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
04/16/2009 03:22 PM
To
Yicheng Jia y...@tmriusa.com
cc
Nicolas Morey-Chaisemartin devel-o...@morey-chaisemartin.com,
general@lists.openfabrics.org
Subject
Re: [ofa-general] link width problem of Qlogic 9024 unmanaged switch
On Thu, Apr
the reset when ports on both side of the link are in INIT state
and LinkUp phys state.
If the disable/wait/enable worked that would've been another story.
It fails too. Both ports go to DOWN after disable is issued and never come
back. How long am I supposed to wait?
Thanks!
Yicheng Jia
Hal
The HCA is Mellanox MHES18-XSC.
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
04/16/2009 06:12 PM
To
Yicheng Jia y...@tmriusa.com
cc
Nicolas Morey-Chaisemartin devel-o...@morey-chaisemartin.com,
general@lists.openfabrics.org
Subject
Re: [ofa-general] link width problem
to DOWN after this. Have you ever tried to run
ibportstate to reset the switch port?
Thanks!
Yicheng Jia
--
Message: 2
Date: Wed, 4 Mar 2009 18:39:54 -0600
From: Randy Halverson randy.halver...@qlogic.com
Subject: [ofa-general] link width problem of Qlogic 9024
Hi Nicolas,
I tried with ibportstate switch lid switch port# reset but I got the
following error:
ibwarn: [19660] mad_rpc: _do_madrpc failed; dport (Lid 7)
ibportstate: iberror: failed: smp set portinfo failed
Have you ever run it successfully on Qlogic 9024 switch?
Thanks!
Yicheng Jia
Hi Nicolas,
Do I need to restart HCA driver if I just use ibportstate to reset the
cable on the switch side?
Thanks!
Yicheng Jia
Nicolas Morey-Chaisemartin de...@morey-chaisemartin.com
04/03/2009 11:47 AM
Please respond to
de...@morey-chaisemartin.com
To
Yicheng Jia y...@tmriusa.com
cc
master_sm_base_lid..0x1
capability_mask.0x2500A6A
IsSMdisabled ports
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
03/26/2009 03:06 PM
To
Yicheng Jia y...@tmriusa.com
cc
general@lists.openfabrics.org, hnr...@comcast.net
Subject
Re: [ofa
stablize communication before OpenSM
starts. Do you have any idea about it?
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
03/27/2009 03:02 PM
To
Yicheng Jia y...@tmriusa.com
cc
general@lists.openfabrics.org, hnr...@comcast.net
Subject
Re: [ofa-general] OpenSM initialization error
switches on different
system, all have the same problem.
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
03/27/2009 03:19 PM
To
Yicheng Jia y...@tmriusa.com
cc
general@lists.openfabrics.org, hnr...@comcast.net
Subject
Re: [ofa-general] OpenSM initialization error
On Fri, Mar
unmanaged switch. Is this
related to hardware?
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
03/26/2009 10:32 AM
To
Yicheng Jia y...@tmriusa.com
cc
general@lists.openfabrics.org, hnr...@comcast.net
Subject
Re: [ofa-general] OpenSM initialization error
On Thu, Mar 26
. It always takes more than 1 minute
for the error disappear.
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
03/26/2009 12:13 PM
To
Yicheng Jia y...@tmriusa.com
cc
general@lists.openfabrics.org, hnr...@comcast.net
Subject
Re: [ofa-general] OpenSM initialization error
It occurs with Qlogic switch, the error is reported on the OpenSM log
file. Both OpenSM and mthca driver are running on QNX environment, so
there's no handy tool available. What else can I do?
Thanks!
Yicheng Jia
Hal Rosenstock hal.rosenst...@gmail.com
03/26/2009 12:53 PM
To
Yicheng Jia
and Cisco SFS7000P switch. Do you know what
the cause is and how to avoid it?
Thanks!
Yicheng Jia
_
Scanned by IBM Email Security Management Services powered by MessageLabs. For
more information please visit http
randomly
occurs in different ports, and if I use Flextronics unmanaged switch, the
problem is gone.
I am wondering if anyone experiences the same problem before, any hint of
how to fix it?
Thanks!
Yicheng Jia
_
Scanned
on OpenSM that's compiled without
HAVE_LIBPTHREAD macro?
Thanks!
Yicheng Jia
_
Scanned by IBM Email Security Management Services powered by MessageLabs. For
more information please visit http://www.ers.ibm.com
Hi Dotan,
Does HCA provide any internal route for local DMA so that local data
transfer doesn't has to go out of the HCA port as regular QPs do? In
another word, it's not efficient to use QPs for local DMA transfer, is it
true?
Thanks!
Yicheng Jia
Software Engineer
Toshiba Medical Research
Hi Folks,
Is it possible to do local DMA transfer using QPs in a single port HCA?
Thanks!
Best,
Yicheng Jia
_
Scanned by IBM Email Security Management Services powered by MessageLabs. For
more information please
Hi Folks,
I have two applications which require different IB transfer rates. I am
using Mellanox 25204 HCA. Can I achieve it by setting up two QPs with
different service levels? Can I set SL field in QP context, or it is
controlled by SM? Thanks!
Best,
Yicheng
Software Engineer
Toshiba
]
10/01/2008 08:05 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org
Subject
Re: [ofa-general] questions about opensm and unmanaged switch
Hi Yicheng,
On 12:35 Wed 01 Oct , Yicheng Jia wrote:
I use opensm with a single unmanaged switch to connect several HCAs. I
Hi Folks,
I use opensm with a single unmanaged switch to connect several HCAs. I
found that HCAs take much longer time to get LID after opensm restart
without power cycle the switch. If the switch is power off/on before
opensm restart, then HCAs get their LIDs sooner. I'm wondering if there's
if there's
minhop table pre-existing in the switch which will prevent HCAs from
regain their LIDs soon. Is there any option to reset the switch during
opensm start?
Thanks!
Yicheng
Hal Rosenstock [EMAIL PROTECTED]
07/10/2008 09:15 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
Jim Mott [EMAIL PROTECTED
,
the only work that opensm does after subnet is up is to log the status.
Thanks!
Yicheng
Hal Rosenstock [EMAIL PROTECTED]
08/27/2008 05:55 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
Dotan Barak [EMAIL PROTECTED], general@lists.openfabrics.org
Subject
Re: [ofa-general] minimum sw components
Hi Hal,
Can opensm just run once? When the subnet is up, it can exit assume that
no change will be made in the subnet.
Thanks!
Yicheng
Hal Rosenstock [EMAIL PROTECTED]
07/10/2008 09:15 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
Jim Mott [EMAIL PROTECTED], general@lists.openfabrics.org
Subject
My operation is quite simple: connect QPs and do RDMA read/write. In this
case, the opensm is not in need when the subnet is up, correct?
Thanks!
Yicheng
Dotan Barak [EMAIL PROTECTED]
08/21/2008 02:33 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
Hal Rosenstock [EMAIL PROTECTED], general
In the past i wrote even more complicated flows than this when the SM
was down...
Can you point to me where it is?
Thanks!
Yicheng
Dotan Barak [EMAIL PROTECTED]
08/21/2008 02:52 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org, Hal Rosenstock [EMAIL PROTECTED
Hi Hal,
I have a question regarding to this issue.
If I have both opensm and Cisco managed switch running in the same subnet,
can opensm automatically detect the Master SM and set itself as the slave
SM? Or I have to manually disable the SM in the Cisco switch in order for
the opensm acts
subnets. It shouldn't be the
case if there's only a single switch in a single subnet. Correct?
Thanks!
Yicheng
Hal Rosenstock [EMAIL PROTECTED]
08/08/2008 01:06 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org
Subject
Re: opensm hang and osmtest report ERR 0130
Hi
Hi Folks,
I have a IB network which consists of only a single unmanaged switch, all
end nodes connecting with the switch only need to do RDMA read/write
operation with each other. My question is, what are the indispensable
modules in driver's core and opensm that make the network up and run?
)? Of cause opensm
need to be customized as well (no SA and CM?).
The reason I'm doing this is I need to port opensm to QNX, I have to use
as little modules as possible.
Best,
Yicheng
Sean Hefty [EMAIL PROTECTED]
07/10/2008 03:25 PM
To
'Yicheng Jia' [EMAIL PROTECTED], general
. If not, reset, up, wait for him to connect
and send something to you.
Is it reliable? I mean the QPs connection will keep alive during the QPs
lifecycle?
Best,
Yicheng
Jim Mott [EMAIL PROTECTED]
07/10/2008 04:17 PM
To
Yicheng Jia [EMAIL PROTECTED], general@lists.openfabrics.org
cc
Subject
RE: [ofa
PROTECTED]
07/10/2008 04:39 PM
To
Jim Mott [EMAIL PROTECTED]
cc
Yicheng Jia [EMAIL PROTECTED], general@lists.openfabrics.org
Subject
RE: [ofa-general] minimum sw components requirement for driver/opensm in a
single unmanaged switch network
On Thu, 2008-07-10 at 14:17 -0700, Jim Mott wrote
[EMAIL PROTECTED]
05/28/2008 12:24 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org
Subject
Re: [ofa-general] MLX HCA: CQ request notification for multiple
completions not implemented?
Yicheng Jia wrote:
Thanks for your reply. I'm using one CQ for all the WRs. Do you know
Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org
Subject
Re: [ofa-general] MLX HCA: CQ request notification for multiple
completions not implemented?
Hi.
Yicheng Jia wrote:
Hi Folks,
I'm trying to use CQ Event notification for multiple completions
(ARM_N) according to Mellanox Lx
Hi Folks,
I'm trying to use CQ Event notification for multiple completions (ARM_N)
according to Mellanox Lx III user manual for scatter/gathering RDMA.
However I couldn't find it in current MLX driver. It seems to me that only
ARM_NEXT and ARM_SOLICIT are implemented. So if there are multiple
Hi Folks,
I have a question regarding to the completion order of RDMA write. Since
RDMA write without Immediate is not handled by responder's RQ WQEs, if two
or more HCAs write to a single HCA simultaneously with this operation,
what the completion order of these RDMA writes would be?
Thanks!
Hi Roland,
Is there SA code available in OFED? I have a IB switch to connect all the
mellanox HCAs, the SA is running on the switch's firmware. My goal is to
skip the switch and use ring topology to connect the HCA with each other.
Is it doable in OFED?
Thanks!
Hal Rosenstock [EMAIL PROTECTED]
02/01/2008 04:25 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
Roland Dreier [EMAIL PROTECTED], general@lists.openfabrics.org
Subject
Re: [ofa-general] SA code?
On Fri, 2008-02-01 at 16:14 -0600, Yicheng Jia wrote:
Hi Roland,
Is there SA code available
!
Yicheng
Hal Rosenstock [EMAIL PROTECTED]
02/01/2008 04:45 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org, Roland Dreier [EMAIL PROTECTED]
Subject
Re: [ofa-general] SA code?
Hi Yicheng,
On Fri, 2008-02-01 at 16:38 -0600, Yicheng Jia wrote:
Hi Hal,
The only reason
Thanks! I think OpenSM is enough for my case.
-Yicheng
Roland Dreier [EMAIL PROTECTED]
02/01/2008 04:20 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org
Subject
Re: SA code?
Is there SA code available in OFED? I have a IB switch to connect all
the
mellanox
Unfortunately I have 9 nodes.
Thanks!
Yicheng
Timothy A. Meier [EMAIL PROTECTED]
02/01/2008 05:39 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org
Subject
Re: [ofa-general] SA code?
Yicheng Jia wrote:
Are you saying all messages are between adjacent neighbors
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org, Roland Dreier [EMAIL PROTECTED]
Subject
Re: [ofa-general] SA code?
On Fri, 2008-02-01 at 17:07 -0600, Yicheng Jia wrote:
Are you saying all messages are between adjacent neighbors on the
ring ?
Yes. Say I have 6 nodes
true, how to set up the fast path operation in the
driver environment?
Thanks!
Yicheng
Roland Dreier [EMAIL PROTECTED]
01/04/2008 02:45 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org, Jack Morgenstein [EMAIL PROTECTED]
Subject
Re: [ofa-general] synchronize commands
, is it true?
Thanks!
Yicheng
Roland Dreier [EMAIL PROTECTED]
01/02/2008 02:52 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org, Jack Morgenstein [EMAIL PROTECTED]
Subject
Re: [ofa-general] synchronize commands issued to MTHCA
Could you tell me what's the difference between
@lists.openfabrics.org
cc
Yicheng Jia [EMAIL PROTECTED], Roland Dreier [EMAIL PROTECTED]
Subject
Re: [ofa-general] synchronize commands issued to MTHCA
On Tuesday 01 January 2008 03:02, Yicheng Jia wrote:
Does your HCA use on-board memory?
(Run: lspci and look at Mellanox lines. You have on-board memory
if you
/2008 12:13 PM
To
Jack Morgenstein [EMAIL PROTECTED]
cc
general@lists.openfabrics.org, Yicheng Jia [EMAIL PROTECTED]
Subject
Re: [ofa-general] synchronize commands issued to MTHCA
Roland, do you think that the memcpy_toio() call might mess things up?
I wouldn't think so, although I don't
the HCA?
Thanks!
Yicheng
Roland Dreier [EMAIL PROTECTED]
01/02/2008 12:13 PM
To
Jack Morgenstein [EMAIL PROTECTED]
cc
general@lists.openfabrics.org, Yicheng Jia [EMAIL PROTECTED]
Subject
Re: [ofa-general] synchronize commands issued to MTHCA
Roland, do you think that the memcpy_toio
PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
Jack Morgenstein [EMAIL PROTECTED], general@lists.openfabrics.org
Subject
Re: [ofa-general] synchronize commands issued to MTHCA
The SW2HW_MPT command is issued while UDAV table is been creating.
During
the time that the driver is waiting
TRACE: mthca_provider.c:460/mthca_ah_create
139906793007 HCR CMD: Status Return: : 3
Do you have any idea?
Thanks and have a good new year!
Yicheng
Roland Dreier [EMAIL PROTECTED]
12/28/2007 11:39 PM
To
Yicheng Jia [EMAIL PROTECTED]
cc
general@lists.openfabrics.org
Subject
Re
Hi Folks,
I'm using mellanox HCA and I'm a newbie to this IB community. I'm
encountering a problem with the HCA board and looking forward to getting
some help here.
I'm using OFED-1.0 and the problem I believe is related to command
synchronization of HCA. The host issues a MAD_INF command at
Hi All,
I'm a newbie to OFED. Can I install OFED-1.2.5 package in cygwin
environment? I got such error when I tried to do it:
Checking dependencies. Please wait ...
ERROR: There are no sources for the 1.5.24(0.156/4/2) kernel installed.
Please install 1.5.24(0.156/4/2) kernel sources to build
56 matches
Mail list logo