I get this trying to
compile uDAPL usinginstall.shwith IBED 1.0 rc3 on RHEL4 U2 2.6.9-22
ppc64:
WARNING: Dapl is not
supported on PPC64 arcitectureWARNING: Dapl is not supported on PPC64
arcitecture
Scott
___
openib-general mailing list
Hello Troy,
it seems that you run into a race condition in our code where we thought
it can never occur. Good catch!
It looks like an event queue is destroyed while on an other CPU an interrupt
is coming in.
We will fix it soon as possible. Thanks for your help!
Regards,
Heiko
Troy
Hi.
I'm working on a dat.conf generator that will search for all of the IB devices
and will create a valid (and updated) dat.conf.
Here is the generated file on a machine with 2 HCAs (2 ports in each device):
# DAT 1.2 configuration file
#
# Each entry should have the following fields:
#
#
Hi,
Does the open Ib support DUAL HCA servers. I tried it on a Sun V20 Z
with dual HCA, but got the HCA failed to come up. I get an yellow
exclamation mark on the HCA. Uninstalling also doesn't help. Any
suggestions ?
Thanks in advance.
Yathi
Hi.
On Wednesday 12 April 2006 12:09, Yathi Shetty (yathiraj) wrote:
Hi,
Does the open Ib support DUAL HCA servers. I tried it on a Sun V20 Z
with dual HCA, but got the HCA failed to come up. I get an yellow
exclamation mark on the HCA. Uninstalling also doesn't help. Any
suggestions ?
On Wednesday 12 April 2006 12:26, Yathi Shetty (yathiraj) wrote:
Hi,
Thank you for the response.
Mellanox 23108, Windows Cluster Compute Edn, Vr.295. Attached a screen
hot.
do you see any error messages on screen or in the /var/log/messages?
I successfully installed on a single HCA.
did
Well. I did not see any error message. The screen shot shows the event
viewer message. I tried vr.300 also. Still the same result.
I am using windows system and have only system logging in event viewer.
Yathi
-Original Message-
From: Dotan Barak [mailto:[EMAIL PROTECTED]
Sent:
Scott Weitzenkamp (sweitzen) wrote:
I get this trying to compile uDAPL using install.sh with IBED 1.0 rc3
on RHEL4 U2 2.6.9-22 ppc64:
WARNING: Dapl is not supported on PPC64 arcitecture
WARNING: Dapl is not supported on PPC64 arcitecture
Scott
--
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
On Wednesday 12 April 2006 13:00, Yathi Shetty (yathiraj) wrote:
Well. I did not see any error message. The screen shot shows the event
viewer message. I tried vr.300 also. Still the same result.
I am using windows system and have only system logging in event viewer.
Yathi
Which OS do you
Quoting r. Michael S. Tsirkin [EMAIL PROTECTED]:
Subject: rma_destroy_id called twice
Sent by mistake, please ignore.
Sorry,
--
MST
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To
Quoting r. Yathi Shetty (yathiraj) [EMAIL PROTECTED]:
Subject: Query on Open IB drivers on DUAL HCA
Hi,
Does the open Ib support DUAL HCA servers. I tried it on a Sun V20 Z
with dual HCA, but got the HCA failed to come up. I get an yellow
exclamation mark on the HCA. Uninstalling also
I am using Windows compute cluster edtn (64bit)
-Original Message-
From: Dotan Barak [mailto:[EMAIL PROTECTED]
Sent: Wednesday, April 12, 2006 3:37 PM
To: Yathi Shetty (yathiraj)
Cc: openib-general@openib.org
Subject: Re: [openib-general] Query on Open IB drivers on DUAL HCA
On
On Wed, 12 Apr 2006, Dotan Barak wrote:
Hi.
I'm working on a dat.conf generator that will search for all of the
IB devices and will create a valid (and updated) dat.conf.
Here is the generated file on a machine with 2 HCAs (2 ports in each
device):
# DAT 1.2 configuration file
#
Hi Yathi,
On 4/12/06, Yathi Shetty (yathiraj) [EMAIL PROTECTED] wrote:
Hi,
Does the open Ib support DUAL HCA servers. I tried it on a Sun V20 Z
with dual HCA, but got the HCA failed to come up. I get an yellow
exclamation mark on the HCA. Uninstalling also doesn't help. Any
suggestions ?
Don wrote,
Looking at the viacheck.c file, it seems that this error is generated when
a bad status is found in the status of a completion queue entry. From the
code=1 , it may be some sort of length
error.This could be coming from the driver or the card, I suppose?
That's as far as I have
http://openib.org/bugzilla/show_bug.cgi?id=35
Summary: 2c_OffloadCheckSum (NDIS) test gives Blue screen
Product: OpenIB
Version: 1.0rc2
Platform: X86-64
OS/Version: Other
Status: NEW
Severity: normal
Priority: P2
http://openib.org/bugzilla/show_bug.cgi?id=35
--- Additional Comments From [EMAIL PROTECTED] 2006-04-12 08:42 ---
Created an attachment (id=10)
-- (http://openib.org/bugzilla/attachment.cgi?id=10action=view)
Minidump file for the blue screen
--- You are receiving this mail
A third option is to keep the RHEL4U3 kernel, and use the OpenIB code
from IBED 1.0 rc3.
Scott
Can you provide more details about this IBED release ? What does the acronym
IBED stand for ?
Is it part of the OpenFabric's 1.0 release, a superset ? what distros it
supports ? etc ?
Seems like a lot
Hi Bryan,
Could you rename the current OpenIB product to OpenIB Linux, and create an
OpenIB Windows project with the following components:
IPoIB
WSD
IB Core
MT23108
MTHCA
Diagnostics
OpenSM
SRP
Utils
Thanks,
- Fab
___
openib-general mailing list
[EMAIL PROTECTED] wrote:
I get this trying to compile uDAPL using install.sh with IBED
1.0 rc3 on RHEL4 U2 2.6.9-22 ppc64:
WARNING: Dapl is not supported on PPC64 arcitecture
WARNING: Dapl is not supported on PPC64 arcitecture
Scott
There are include files that map DAT-defined types
to
I have started writing a simple RDMA app which uses the rdmacm. I have gotten
the connection established, QP's and MR's set up, and have sent the RDMA ETH.
However, more and more I am getting the RNR Retry Counter Exceeded error back
from the client's post send of the RDMA ETH. About 1/10 times
On Wed, 2006-04-12 at 09:40 -0700, Fab Tillier wrote:
Could you rename the current OpenIB product to OpenIB Linux, and create an
OpenIB Windows project with the following components:
IPoIB
Added.
WSD
I need a description for this.
IB Core
Added.
MT23108
Need description.
MTHCA
On Wed, 2006-04-12 at 09:40 -0700, Fab Tillier wrote:
Could you rename the current OpenIB product to OpenIB Linux, and create an
OpenIB Windows project with the following components:
I forgot to mention that I renamed OpenIB to OpenFabrics Linux, and
created OpenFabrics Windows for Windows
On 4/12/06, Bryan O'Sullivan [EMAIL PROTECTED] wrote:
On Wed, 2006-04-12 at 09:40 -0700, Fab Tillier wrote:
WSD
I need a description for this.
Windows Sockets Direct provider, Microsoft's precursor to SDP.
MT23108
Need description.
VAPI-based Mellanox HCA driver for Tavor (and Arbel
As a follow up, can you add the following operating systems:
Windows Server 2003, x86
Windows Server 2003, x64
Windows Server 2003, IA64
Windows XP, x86
Windows XP, x64
Is there a way to make OS choices project specific, just like the components?
Thanks!
- Fab
On Wed, 2006-04-12 at 09:51 -0700, Fabian Tillier wrote:
Windows Sockets Direct provider, Microsoft's precursor to SDP.
Thanks. Added.
MT23108
Need description.
VAPI-based Mellanox HCA driver for Tavor (and Arbel in Tavor compatibility
mode)
Mmm, rolls right off the tongue :-)
On Wed, 2006-04-12 at 09:53 -0700, Fabian Tillier wrote:
As a follow up, can you add the following operating systems:
No, sorry.
The version of Bugzilla at openib.org has a brain-dead schema where some
categories of stuff live in the database, while others live in a hunk of
Perl that you have
I forgot to give you maintainers, added below.
On 4/12/06, Fab Tillier [EMAIL PROTECTED] wrote:
IPoIB
me
WSD
me
IB Core
me
MT23108
Leonid Keller ([EMAIL PROTECTED])
MTHCA
Leonid Keller ([EMAIL PROTECTED])
Diagnostics
I guess assign these to me for now.
OpenSM
Probably same as for
On Mon, 2006-04-10 at 11:04, Jack Morgenstein wrote:
A couple of commentary comments below...
-- Hal
Index: src/drivers/infiniband/core/mad.c
===
--- src/drivers/infiniband/core/mad.c (revision 6066)
+++
Thanks applied queued for 2.6.17
___
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
All,
The OpenFabrics Enterprise Working Group is pleased to announce the
creation of the OpenFabrics Enterprise Distribution (OFED). This was
approved today by the Board of Directors.
OFED is a distribution of InfiniBand software that includes, or is a
superset of, the OpenFabrics 1.0 release,
On Wed, 2006-04-12 at 15:02, Shawn Hansen (shahanse) wrote:
I have some questions about OFED:
--
Frequently Asked Questions
--
Q: Is OFED development happening in the open?
- Yes, OFED uses the OpenFabrics bugzilla for bug reporting, and
Apr 7 18:17:17 lab105 kernel: Unable to handle kernel paging request at
virtual address 6b6b6b6b6b6b6b6b
I think I fixed the bug causing this oops (I was able to reproduce it,
and I don't see it any more). I checked the following patch in and
queued it for kernel 2.6.17:
diff-tree
http://openib.org/bugzilla/show_bug.cgi?id=35
[EMAIL PROTECTED] changed:
What|Removed |Added
AssignedTo|[EMAIL PROTECTED] |[EMAIL PROTECTED]
When I do a ibping I get an error (on a 32 bit machine)
Linux Kernel: 2.6.16
infiniband directory replaced with SVN6446
I enable debug in umad.c, I get the following error. The ioctl call to the umad driver (umad device)
is failing.
return value for ioctl is -1, errno is -22 (EINVAL)
portid 0
On Wed, 12 Apr 2006 15:12:28 -0400
Hal Rosenstock [EMAIL PROTECTED] wrote:
On Wed, 2006-04-12 at 15:02, Shawn Hansen (shahanse) wrote:
I have some questions about OFED:
--
Frequently Asked Questions
--
Q: Is OFED development
Vu Here is my status of testing this patch. On x86-64 system I
Vu got data corruption problem reported after ~4 hrs of running
Vu Engenio's Smash test tool when I tested with Engenio storage
Vu On ia64 system I got multiple async event 3
Vu (IB_EVENT_QP_ACCESS_ERR) and
Roland Dreier wrote:
Apr 7 18:17:17 lab105 kernel: Unable to handle kernel paging request at
virtual address 6b6b6b6b6b6b6b6b
I think I fixed the bug causing this oops (I was able to reproduce it,
and I don't see it any more). I checked the following patch in and
queued it for kernel
I am not having much luck with the default RHEL4U3 setup. I
appear to have IP over IB running and appearing to work, but
am unable to get any mpi variants to work directly with IB, I
do have it working over tcp with ch_p4.
With mvapich-0.9.7 it errors out in the building
stage with an error
Ira wrote,
How can that be ? The 1.0 branch contains no kernel code. Where is the
OFED kernel code kept ?
This is my one big question.
Also what happens to people who took the 1.0 branch and are actually using
it?
That is what LLNL has done and now the kernel code is gone.
Confused,
Ira
Uh
The RMPP version needs to be 1.
[EMAIL PROTECTED] src]# svn diff ibping.c
Index: ibping.c
===
--- ibping.c (revision 6446)
+++ ibping.c (working copy)
@@ -336,7 +336,7 @@
exit(0);
}
- if (mad_register_client(ping_class, 0) 0)
+
Since the 1.0 RC2 tag in SVN contains kernel code (which led to
confusion), and Hal wanted to get a few more diag-related changes into
RC2 for people to use, we are tossing around the idea of tagging another
release candidate. I've suggested calling it RC2.1, since it's only
slightly different
OFED is focused on including open-source MPI in the distribution.
Commercial MPI ISVs can definitely test against OFED, make statements
about interoperability, and ask the community to make changes specific
to their stack. Likewise, IB vendors may directly do their own testing
with these MPI
Linus, please pull from
master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git for-linus
This tree is also available from kernel.org mirrors at:
git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git
for-linus
This includes changes that I've asked you to pull a
OFED is focused on including open-source MPI in the distribution.
Commercial MPI ISVs can definitely test against OFED, make statements
about interoperability, and ask the community to make changes specific
to their stack. Likewise, IB vendors may directly do their own testing
with these MPI
I was working with someone and watching a 256-node bproc cluster boot
friday. The openib folks have done a lot of very nice work. It booted
quite well once we set hoq and slv to 17 in the voltaire switch. It was
really snappy coming up. It was actually as fast to boot as a myrinet
cluster,
Bryan wrote,
Does anyone have any objections?
By the way, Tziporet and I have discussed syncing up the release
candidate numbers for the next IBED and OF release candidates, to reduce
a possible source of confusion. This will mean that OF will hop from
RC2.1 to RC4, while IBED will step to RC4.
Ira This is my one big question.
Ira Also what happens to people who took the 1.0 branch and are
Ira actually using it? That is what LLNL has done and now the
Ira kernel code is gone.
Kernel code was included on the branch by mistake. OpenFabrics is not
in the business of
On Wed, 2006-04-12 at 18:25, Viswanath Krishnamurthy wrote:
The RMPP version needs to be 1.
Thanks. I'm not sure what changed here to require this. I need to do
some more digging.
-- Hal
[EMAIL PROTECTED] src]# svn diff ibping.c
Index: ibping.c
The mad_register_agent function in mad.c kernel file was checking for rmpp_version.
This was failing and this failure was propagated to umad (thru ioctl)
On 12 Apr 2006 20:46:33 -0400, Hal Rosenstock [EMAIL PROTECTED] wrote:
On Wed, 2006-04-12 at 18:25, Viswanath Krishnamurthy wrote: The RMPP
Hello Roger,
With mvapich-0.9.7 it errors out in the building
stage with an error ibv_free_device_list/ibv_get_device_list missing,
I cannot find any of the ib libraries on RHEL4U3 that appear to contain
that library.
Thanks for trying out MVAPICH-0.9.7. Currently, we don't have any
machine
Hello Don,
We are running RHEL4 U3 and the MVAPICH version from the OpenIB gen2 trunk.
We
were able to run the OSU benchmark tests (osu_bw, osu_bibw, and osu_latency)
with the Mellanox SDR cards successfully, but when we swapped out the cards
for
DDR cards, we ran into some problems. We
mad.c::ib_register_mad_agent: Fix RMPP version check during agent
registration
Only check that RMPP version is not specified when MAD class does not
support RMPP
Signed-off-by: Hal Rosenstock [EMAIL PROTECTED]
--
Roland,
Can you push this fix upstream ? Thanks.
Index: mad.c
On Wed, 2006-04-12 at 20:46, Hal Rosenstock wrote:
On Wed, 2006-04-12 at 18:25, Viswanath Krishnamurthy wrote:
The RMPP version needs to be 1.
Thanks. I'm not sure what changed here to require this. I need to do
some more digging.
I figured it out. The fix is in r6448. Can you update and
On Wed, 2006-04-12 at 21:07, Viswanath Krishnamurthy wrote:
The mad_register_agent function in mad.c kernel file was checking for
rmpp_version.
This was failing and this failure was propagated to umad (thru ioctl)
Right. Just because a class is allowed to use RMPP doesn't mean that
Hal Rosenstock wrote:
hoq is HOQLife. Is slv the switch LifeTimeValue ?
I believe so.
Does that have anything to do with those settings ?
it would not work until hoq and slv were 17.
Truly hanging ?
yes, and it was the only real connection at that point, from the bproc
daemon on the
OK, I updated my rdma_cm branch with all of this.
In addition I put the following in -- it's idiomatic in the kernel to
let the compiler handle htons(A_CONSTANT) in code. Should I commit
this to svn too?
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index
OK, I applied this by hand ... your mailer turned all your tabs into
spaces somewhere along the way, so the patch wouldn't apply.
- R.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To
59 matches
Mail list logo