Hi Sean,
I installed the latest kernel:2.6.17.11 and the latest ib stack: rev 9240
When I compile programs with rdmacm library, I get the error: (though the
program runs fine...)
/usr/bin/ld: warning: libibverbs.so.1, needed by
/usr/local/lib/librdmacm.so, may conflict with libibverbs.so.2
Does
Hi,
We were wondering if a similar patch is applied to the iWARP side. This
functionality is very useful,
Thanks,
Amith
-- Forwarded message --
Date: Thu, 13 Jul 2006 16:31:56 -0700
From: Sean Hefty <[EMAIL PROTECTED]>
To: openib-general@openib.org
Cc: 'amith raji
message --
Date: Thu, 22 Jun 2006 09:45:26 -0400 (EDT)
From: amith rajith mamidala <[EMAIL PROTECTED]>
To: Hal Rosenstock <[EMAIL PROTECTED]>
Cc: Sean Hefty <[EMAIL PROTECTED]>
Subject: Re: Multicast Addresses
Hi Hal,
IPoIB interface is started. I can ping to other nodes using
I was checking rping with the latest stack. The client exits normally, the
server still hangs after printing the cq status.
server ping data: rdma-ping-9: JKLMNOPQRSTU
server DISCONNECT EVENT...
wait for RDMA_READ_ADV state 9
cq completion failed status 5
When I kill the process and restart the s
Hi,
I have a quick question. I updated the infiniband kernel modules and while
compiling them got this error.
(Redhat AS 4, linux-2.6.16.20 on IA-32 platform )
drivers/infiniband/ulp/ipoib/ipoib_main.c: In function
`ipoib_neigh_setup_dev':
drivers/infiniband/ulp/ipoib/ipoib_main.c:794: error: str
wrote:
> On Fri, 2006-06-16 at 11:20 -0400, amith rajith mamidala wrote:
> > Hi Steve,
> >
> > The rping also doesn't exit after printing these error messages. Is this
> > expected?
> >
>
> It should exit! :-(
>
> Maybe rping is not acking all th
>
> On Thu, 2006-06-15 at 17:24 -0400, amith rajith mamidala wrote:
> > Hi,
> >
> > With the latest rping code (Revision: 8055) I am still able to see this
> > race condition.
> >
> > server side:
> >
> > [EMAIL PROTECTED] examples]$
Hi,
With the latest rping code (Revision: 8055) I am still able to see this
race condition.
server side:
[EMAIL PROTECTED] examples]$ ./rping -s -vV -C10 -S26 -a 0.0.0.0 -p 9997
server ping data: rdma-ping-0: ABCDEFGHIJKL
server ping data: rdma-ping-1: BCDEFGHIJKLM
server ping data: rdma-ping-2:
Hi,
I have installed the latest infiniband stack with 2.6.16.20 kernel.
I tested the installation using ibv_rc_pingpong and it works fine.
But, while trying to use rping, I get the following error:
librdmacm: couldn't open rdma_cm ABI version.
rdma_create_event_channel error 2
Any clues as to wh
Hi Sean,
I am planning to use RDMA CM for multicast functionality. It would be
great if you can point me to a simple multicast test program using
RDMA CM?
Thanks,
Amith
On Fri, 9 Jun 2006, Sean Hefty wrote:
> Sean Hefty wrote:
> > This patch series enhances support for joining and leaving multi
MVAPICH uses multicast support. It doesnot use SA queries currently. But,
we plan to use this feature for multicast in the future,
Thanks,
Amith
On 4 May 2006, Hal Rosenstock wrote:
> On Thu, 2006-05-04 at 14:41, Greg Johnson wrote:
> > On Thu, May 04, 2006 at 01:48:29PM -0400, Hal Rosenstock w
Hi Sean,
I have a few basic questions:
1. Does the API which waits for join to complete
ensure that the multicast forwarding tables in the switches have been
updated. This is one of the main problems that we had studied:
(Please refer to the following EURO PVM/MPI paper for details)
http://www.cs
Hi,
I was trying to install the latest gen2 with 2.6.16 kernel
(kernel.org). During make, I encountered the
following warning:
*** Warning: "rdma_wq" [drivers/infiniband/core/ib_local_sa.ko] undefined!
Running the ibv_rc_pingpong test, I get the following error
local address: LID 0x0005, QPN 0x
I have a question related to the mixture of HCA bandwidths
in the fabric. For an upper layer, like MVAPICH, "negotiating"
for a rate so that all the ports are "involved" can be quite
expensive, especially if the code falls in the critical path.
Can any additional support be provided by the underly
Hi,
> * MVAPICH uses a multicast group for some MPI collectives
> * This can be turned off by setting env var DISABLE_HARDWARE_MCST
MVAPICH uses h/w multicast for MPI_Bcast. We plan to extend this to other
collectives in future,
Thanks,
Amith
>
> * An IB multicast group has to use ports of th
; -Original Message-
> > From: [EMAIL PROTECTED] [mailto:openib-general-
> > [EMAIL PROTECTED] On Behalf Of amith rajith mamidala
> > Sent: Saturday, January 28, 2006 11:19 PM
> > To: Hal Rosenstock
> > Cc: [EMAIL PROTECTED]; openib-general@openib.org
> > Su
;
> On Sat, 2006-01-28 at 12:46, amith rajith mamidala wrote:
> > Hi,
> >
> > I was able to create multicast groups after Hal's fix. But, when I do join
> > subsequently from the same program I am getting a port_alloc error:
> >
> > Jan 28 12
Hi,
I was able to create multicast groups after Hal's fix. But, when I do join
subsequently from the same program I am getting a port_alloc error:
Jan 28 12:22:12 119632 [AB2223C0] -> osm_vendor_bind: Binding to port
0x627051005.
-I- Created the Multicast Group:
MGID..
I was trying to modify a UD QP to init state and the modify call
was failing with an error code of 22, I am including the code snippet
which does create/ modify of the QP:
memset (&qp_init_attr, 0, sizeof (qp_init_attr));
qp_init_attr.cap.max_recv_wr = 100;
qp_init_attr.cap.max_send_w
Hi,
I am trying to run a program which creates multicast groups. I am using
the libraries -losmcomp -losmvendor -lopensm for this purpose.
I was facing a problem while running the program. However,
the program runs if I execute it as a root. I am using the revision
4918 of the osm related librari
> An alternative is to provide UD and multicast/broadcast support in the CMA. I
> know that the Intel MPI runs over DAPL, which does not provide multicast
> support. Can MPI operate with unreliable multicast support? Does MPI plan on
> using IB multicast?
Yes, the MPI can operate with unreliab
Hi,
We have incorporated the gcc version 4 patch into the openib svn.
Thanks,
Amith,Weikuan
On Mon, 26 Sep 2005, Roland Dreier wrote:
> gcc version 4 doesn't like the extern declaration of free_vbuf_head to
> followed by a static declaration in vbuf.c. To fix this, we can just
> get rid of t
Hi,
We have been testing gen2 installation using the mem-free IBA cards from
Mellanox. We were able to successfully run InfiniBand tests over this
installation. When we replaced the IBA mem-free with the mem cards
(no software changes), the ports are in the disabled state and ibstatus shows
the f
L="issm*", NAME="infiniband/%k"
KERNEL="uverbs*", NAME="infiniband/%k", MODE="0666"
--
Is this the cause for the problem ?
Thanks,
Amith
On Thu, 14 Jul 2005, Matt Leininger wrote:
> On Fri, 2005-07-15 at 01:47 -0400, amith ra
Hi,
We have installed the latest openib stack (Rev:2861) on the X86_64
platform. While running the pingpong tests I am encountering the
following error:
libucm: Error <-1:2> couldn't open IB cm device
[1] Abort: Error getting HCA context
I am not sure why this happening ?
Thanks,
Amith
_
Hi,
I am getting an error while destroying the CQ. I am not able to figure out
the reason why I am getting this error. I printed out the error code and
it is 16. Is there anyway by which I can capture the error message and not
just the code ?
Thanks,
Amith
___
26 matches
Mail list logo