> > > > > > > > We are using kernel 2.6.16.3 and installed the latest
> > > > > > > > code/drivers from
> > > > > > > > the iwarp branch. Currently, we are seeing an address
> > > > > > > > resolution problem
> > > > > > > > while using rping.
> > > > > > > >
> > > > > > > > [EMAIL PROTECTED] exa
The server log indicates the T3 RNIC got the listen command for port
. The client log, however, shows no activity. So I _think_ there
is still some configuration problem and the RDMA CMA is choosing the
wrong rdma interface for the outgoing connection. Its certainly _not_
choosing the T3 rn
Sorry attached the wrong server log. Here are the new logs.
--Sundeep.
On Thu, 20 Jul 2006, Sundeep Narravula wrote:
> Steve,
>
> > > Please build the iw_cxgb3 driver with debug on and send me
> > > the /var/log/messages snipits after running rping. That'll help me
> > > figure out what's up
Steve,
> > Please build the iw_cxgb3 driver with debug on and send me
> > the /var/log/messages snipits after running rping. That'll help me
> > figure out what's up...
I have attached the logs on the server side and the client side.
Thanks,
--Sundeep.
>
> I will try this and get back.
>
> T
Kim, looks good.
Do we plan to have any end-user talking about their experiences,
requirements, etc. Also, a common comment we've heard from previous
events is stability and quality of OFA stack. Can we talk about
"testing/validation and release process"?
just a thought.
Tuan Phamdo
Server Platf
Hi Sasha, Hal,
Good catch!
Eitan
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
If a SEND is received on a QP and it generates a BOUNDS violation
because the recv buffer posted is too small, will this generate an async
error?
I've written a program to generate this event, and I get the appropriate
completion status (IBV_WC_LOC_LEN_ERR), but I'm not getting any poll
event on
Hi Steve,
> What firmware version are you using? You might need to contact Chelsio
> and get the correct firmware for the openib drivers. ethtool -i will
> show us what version you're using. It should say something like this:
>
> vic21:~ # ethtool -i eth2
> driver: cxgb3
> version: 1.0.0
> fir
On Thu, 2006-07-20 at 12:39 -0400, Sundeep Narravula wrote:
> Hi,
>
> > Hi Sundeep,
> > What is the output of 'ibv_devices' ? (its in libibverbs/examples)
>
> This is the output of ibv_devices.
>
> [EMAIL PROTECTED] examples]$ ./ibv_devices
> libibverbs: Warning: couldn't load driver
> /usr/lo
Hi,
> Hi Sundeep,
> What is the output of 'ibv_devices' ? (its in libibverbs/examples)
This is the output of ibv_devices.
[EMAIL PROTECTED] examples]$ ./ibv_devices
libibverbs: Warning: couldn't load driver
/usr/local/lib/infiniband/amso.so: /usr/local/lib/infiniband/amso.so:
undefined symbol:
--
MST
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Title: Message
in the kernel code: cma.c:
#define CMA_VERSION 0x00
I’m looking for the version in the rdma_ucm module. Do you see an
rdma_cm directory under /sys/class/misc or /sys/class/infiniband?
___
openib-general mailing list
o
OpenSM/complib: Fix memory corruption in cl_pool.c:cl_qcpool_init
This affects big endian 64-bit architectures (it's covered up on little
endian 64-bit architectures).
Signed-off-by: Sasha Khapyorsky <[EMAIL PROTECTED]>
Signed-off-by: Hal Rosenstock <[EMAIL PROTECTED]>
Index: complib/cl_pool.c
Quoting r. Arne Redlich <[EMAIL PROTECTED]>:
> Subject: Re: [openib-general] [PATCH 2/2] ib_cm: fix REJ due to invalid GID
>
> Am Mittwoch, den 19.07.2006, 20:05 +0300 schrieb Michael S. Tsirkin:
> > Quoting r. Arne Redlich <[EMAIL PROTECTED]>:
> > > Subject: Re: [openib-general] [PATCH 2/2] ib_cm
Am Mittwoch, den 19.07.2006, 20:05 +0300 schrieb Michael S. Tsirkin:
> Quoting r. Arne Redlich <[EMAIL PROTECTED]>:
> > Subject: Re: [openib-general] [PATCH 2/2] ib_cm: fix REJ due to invalid GID
> >
> > Am Dienstag, den 18.07.2006, 12:21 -0700 schrieb Sean Hefty:
> > > Arne Redlich wrote:
> > > >
On Wed, 2006-07-19 at 23:51 -0700, Sean Hefty wrote:
> I executed the example ucmatose and got the following failure:
>
>
>
>
>
> # ucmatose
> librdmacm: couldn't read ABI version.
> failed to create event channel
Make sure rdma_ucm is loaded. Without that module, you'll get that
error...
The ifconfig stuff looks ok. thanks for sending it.
What firmware version are you using? You might need to contact Chelsio
and get the correct firmware for the openib drivers. ethtool -i will
show us what version you're using. It should say something like this:
vic21:~ # ethtool -i eth2
dri
Sundeep Narravula wrote:
> Hi,
>
> We are using kernel 2.6.16.3 and installed the latest code/drivers from
> the iwarp branch. Currently, we are seeing an address resolution problem
> while using rping.
>
> [EMAIL PROTECTED] examples]$ ./rping -c -VvC100 -a 150.10.11.200 -p
> libibverbs: War
To clarify, I am attempting to not duplicate any function, though data
structures will get duplicated (with the knowledge that one set will be
removed at some stage). The idea is to define all rdma_* functions
and make the exported ibv_ functions call these rdma_ exported API's.
(eg :
ibv_cmd_creat
Or Gerlitz wrote:
> Hi Tziporet,
>
> Do you have an initial drop of the bonding solution planned for OFED 1.1
> that is ready to see the daylight? if not, when is this expected?
>
> As i mentioned to you, we are investigating few possible ways to
> implement HA for IPoIB and want to examine your
Hi Or,
I am working on IPoIB failover.
I tried Michael's Tsirkin patch for ipoib (updating neighbor structure)
and it fixes the issue Roland was talking about.
Meanwhile I have tested the following flow:
/*_Setup description:_*/
host1 - 2 IB ports connected to IB switch.
ib0: 11
Title: Message
I executed the example ucmatose
and got the following failure:
# ucmatoselibrdmacm: couldn't
read ABI version.failed to create event channel
it seems that the cma kernel
module don't create any ABI file, but the user level
library
Quoting r. Sean Hefty <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] ib_cm: fix REJ due to invalid GID
>
> Michael S. Tsirkin wrote:
> > Should we be worried that this also sends IB_CM_REJ_INVALID_GID if
> > find_cached_pkey fails?
>
> I'm not sure that an invalid pkey necessarily maps better to any
Hi,
Are you are OK with :
1. Changing all non-exported routines in libibverbs to the new API.
All static functions can be changed immediately instead of going
the "deprecation" way.
2. Adding new duplicate API's for those API's that are exported to
other libraries.
Is this the right
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> > [PATCH] IB/mad: validate MADs for spec compliance C13-18.1.1
>
> Seems fine but I wonder why the ib_response_mad function moved into a
> public header.
OK, the problem was that a file using it was missing from a commit. Sorry.
I have updated the
sorry
--
MST
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Hi,
> What does your network configuration look like? IE send ifconfig output
> on both systems.
> Send the output of lsmod on both systems.
I have attached both these for both the systems.
> Does krping work?
No. It fails with the same error.
> Can you ssh between the 2 systems using the T3
27 matches
Mail list logo