> Quoting Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: [PATCHv6 RFC] IPoIB CM Experimental support
>
> Looks pretty good, but one thing worries me:
>
> Overall looks great, I'll merge it up.
Great, thanks!
Just to clarify: do you intend to fix up the comments below or do you prefer for
me t
> Quoting Steve Wise <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] [RFC] ofed_1_2 - SLES9SP3 Backport -IWCM workaroundfor
> ip_dev_find() bug.
>
> Here it is (only tested with rping over iWARP on sles9sp3):
>
>
>
>
> xxx_ip_dev_find() must use scope HOST.
>
> From: Steve Wise <
(I had submitted this once earlier but got no response)
cm_conn_req_handler() :
1. Calling destroy_cm_id leaks 3 work 'free' list entries.
2. cm_id is freed up wrongly and not cm_id_priv (though the
effect is the same since cm_id is the first element of
cm_id_
On Tue, 2007-02-06 at 16:14, Michael Arndt wrote:
> Sorry,
>
> there was a little mistake.
I think I understand what you are saying now. The below are the 2
responses you get.
> The orginal packet has the initial path [0][1][1], return path [0][2][2],
> hop count and hop pointer are 2 (SubnGetRe
Here it is (only tested with rping over iWARP on sles9sp3):
xxx_ip_dev_find() must use scope HOST.
From: Steve Wise <[EMAIL PROTECTED]>
Function xxx_ip_dev_find(RT_SCOPE_LINK) returns the wrong interface on
some kernels. The correct scope is RT_SCOPE_HOST.
Signed-off-by: Ste
Looks pretty good, but one thing worries me:
Overall looks great, I'll merge it up. A few quick questions: > +#ifdef
CONFIG_IPV6
I think this really needs to be
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
but I'm not clear on what happens if IPoIB is built-in and IPv6 is
built as
On Wed, 2007-02-07 at 00:12 +0200, Michael S. Tsirkin wrote:
> > Quoting Steve Wise <[EMAIL PROTECTED]>:
> > Subject: Re: [PATCH] [RFC] ofed_1_2 - SLES9SP3 Backport -IWCM workaroundfor
> > ip_dev_find() bug.
> >
> > On Tue, 2007-02-06 at 23:36 +0200, Michael S. Tsirkin wrote:
> > > > How shall I
> Is this the response ? If so, what's the status ? What is the attribute
> ID ?
yes its a response. The attribute is NodeInfo or Portinfo or what ever...the
attribute ID didn't change from the original packet (first receive). The
status is 0 and the D-Bit is set, because it is a response.
>> Th
> Quoting Steve Wise <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] [RFC] ofed_1_2 - SLES9SP3 Backport -IWCM workaroundfor
> ip_dev_find() bug.
>
> On Tue, 2007-02-06 at 23:36 +0200, Michael S. Tsirkin wrote:
> > > How shall I fix this?
> >
> > Patch?
> >
>
> Riiight. I'm afraid if I use HOST
On Tue, 2007-02-06 at 23:36 +0200, Michael S. Tsirkin wrote:
> > How shall I fix this?
>
> Patch?
>
Riiight. I'm afraid if I use HOST instead of LINK that I'll break some
strange SDP loopback feature or some such thing. And I'm not in a
position to test that.
But I can post a patch. Shall
On Tue, 2007-02-06 at 16:14, Michael Arndt wrote:
> Sorry,
>
> there was a little mistake.
>
> The orginal packet has the initial path [0][1][1], return path [0][2][2],
> hop count and hop pointer are 2 (SubnGetResp), the Dr_DLID and DrSLID are
> permissive.
Is this the response ? If so, what's
> How shall I fix this?
Patch?
--
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
How shall I fix this?
I think the correct scope is RT_SCOPE_HOST.
Anyone know why RT_SCOPE_LINK was chosen?
On Tue, 2007-02-06 at 15:17 -0600, Steve Wise wrote:
> > Try copying inet_select_addr source in from some upstream kernel,
> > look at that.
> >
>
> It appears that xxx_ip_find_dev()
> Try copying inet_select_addr source in from some upstream kernel,
> look at that.
>
It appears that xxx_ip_find_dev() should be calling inet_select_addr
with RT_SCOPE_HOST and not RT_SCOPE_LINK. Everything works fine for me
if I change xxx_ip_find_dev() to use RT_SCOPE_HOST.
>From the hea
Sorry,
there was a little mistake.
The orginal packet has the initial path [0][1][1], return path [0][2][2],
hop count and hop pointer are 2 (SubnGetResp), the Dr_DLID and DrSLID are
permissive.
The packet I asking for has the initial path [0][0][0], return path
[0][0][0],
hop count and hop po
Hi,
> Guess you don't mean IB router when you say router in your description.
yes
> Is the sender a normal node ? Is normal node mean standard OpenIB
> without changes ? How was the SMI changed ? On which nodes ? Only the
> intermediate one ?
Yes, the sender is a normal node without any changes.
> Quoting Steve Wise <[EMAIL PROTECTED]>:
> Subject: Re: [openib-general] [PATCH] [RFC] ofed_1_2 - SLES9SP3 Backport
> -IWCM workaround for ip_dev_find() bug.
>
> > > >
> > > > Can we just backport our own version of ip_dev_find()? We had this
> > > > once before
> > > > in svn when they remo
> > >
> > > Can we just backport our own version of ip_dev_find()? We had this once
> > > before
> > > in svn when they removed it from being exported from the kernel.
> >
> > Yes, this is in kernel_addons for 2.6.19 or something like that.
> > Just copy from there, much cleaner than the patch
Thanks Roland, I will apply the patch to the customer's cluster.
The problem I found when failover bringing the new IPoIB interface up
in the existing fabric, with a limit number of multicast join groups from
our configuration, the interface can join broadcast group successfully,
> I guess my first reaction is "don't do that."
eg look at http://www.gnu.org/software/libc/manual/html_node/Nonreentrancy.html
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe,
> > Can you comment on the multicast changes merge for 2.6.21 status?
>
>Where are the final patches that you want to merge?
Try the for-roland branch at git.openfabrics.org/~shefty/scm/rdma-dev.git. If
this doesn't work, or you hit any snags, let me know, and I'll try to correct
any issues so th
> #0 0x003a6ce09172 in pthread_spin_lock () from
> /lib64/tls/libpthread.so.0
> #1 0x002a959cf449 in mthca_cq_clean (cq=0x607240, qpn=3277830, srq=0x0)
> at src/cq.c:554
> #2 0x002a959d28b9 in mthca_destroy_qp (qp=0x607400) at src/mthca.h:246
> #3 0x0040117b in clien
> Here is the patch, if possible please give your input asap, we have an
> urgent customer issue need to be resolved:
I guess this is OK, but what is the urgent issue it fixes?
- R.
___
openib-general mailing list
openib-general@openib.org
http://op
No specific problems using the 2 just questioning, I've been looking at
other stuff recently.
I'm trying a single server to:
1. Connect Lustre servers using ipoib and
2. recognize the IB storage using srp.
all the ibv_xx_ping_pong routines work between servers. Pings usin
> Can you comment on the multicast changes merge for 2.6.21 status?
Where are the final patches that you want to merge?
- R.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe,
On Tue, 2007-02-06 at 21:22 +0200, Michael S. Tsirkin wrote:
> > Quoting Sean Hefty <[EMAIL PROTECTED]>:
> > Subject: Re: [PATCH] [RFC] ofed_1_2 - SLES9SP3 Backport - IWCM workaround
> > for ip_dev_find() bug.
> >
> > > Actually, yes it does. Here's one case (that I just tested :):
> > >
> > >
> Is there anything that prevents 2 ULPs - srp and ipoib - from running
> simultaneously on the same port in OFED 1.1.1?
No, there isn't. Are you seeing problems trying it?
- R.
___
openib-general mailing list
openib-general@openib.org
http://openi
https://bugs.openfabrics.org/show_bug.cgi?id=347
Summary: rdma cm backport to EL4 - U3 broken
Product: OpenFabrics Linux
Version: 1.2
Platform: X86-64
OS/Version: RHEL 4
Status: NEW
Severity: blocker
Priority: P1
Is there anything that prevents 2 ULPs - srp and ipoib - from running
simultaneously on the same port in OFED 1.1.1?
If so what about different ports on the same hca?
Timothy Snider
Storage Architect
Strategic Planning, Technology and Architecture
LSI Logic Corporation
3718 North Rock Road
Wich
> Quoting Sean Hefty <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] [RFC] ofed_1_2 - SLES9SP3 Backport - IWCM workaround for
> ip_dev_find() bug.
>
> > Actually, yes it does. Here's one case (that I just tested :):
> >
> > If you rdma_bind() to an explicit address local address, it will fail.
> >
I already opened one for the libibverbs.d problem. 339
On Tue, 2007-02-06 at 10:54 -0800, Scott Weitzenkamp (sweitzen) wrote:
> libibverbs is not working. I have opened bugs 342-346 for the issues
> I've found so far:
>
> # ibv_devices
> libibverbs: Warning: couldn't open config directory
> '/
Thanks, queued in my tree for 2.6.21
___
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
libibverbs is not working. I have opened bugs 342-346 for the issues
I've found so far:
# ibv_devices
libibverbs: Warning: couldn't open config directory
'/usr/local/ofed/etc/libibverbs.d'.
libibverbs: Warning: no userspace device-specific driver found for
/sys/class/in
finiband_verbs/uverbs0
> Actually, yes it does. Here's one case (that I just tested :):
>
> If you rdma_bind() to an explicit address local address, it will fail.
>
> Foo!
>
> I guess I'll need to address the uses of ip_dev_find() in addr.c as well
> before we commit this.
Can we just backport our own version of ip_
opened bug 340.
On Mon, 2007-02-05 at 19:07 -0600, Steve Wise wrote:
> I think there might be some dependency problem. I selected libibverbs,
> libcxgb3, librdmacm, perftest, mvapich2/IWARP and mpitests. For some
> reason it pulled in libibumad as a prereq, but not libibcommon...
>
> Also, I t
On Tue, 2007-02-06 at 09:37 -0800, Sean Hefty wrote:
> Steve Wise wrote:
> > I propose the following fix for supporting iWARP on SLES9SP3.
> >
> > This fixes bug 325.
> >
> > Sean, can you please review this?
>
> The changes seem fine with me.
>
> Does this bug affect the ib_addr module as
Steve Wise wrote:
> I propose the following fix for supporting iWARP on SLES9SP3.
>
> This fixes bug 325.
>
> Sean, can you please review this?
The changes seem fine with me.
Does this bug affect the ib_addr module as well? (addr_resolve_local and
rdma_translate_ip)
- Sean
_
sdpnetstat is getting added to the dapl-devel RPM.
# rpm -qlip dapl-devel-1.2.0-0.x86_64.rpm
Name: dapl-devel Relocations: (not
relocatable)
Version : 1.2.0 Vendor: OpenFabrics
Release : 0 Build Date: Mon 05
I propose the following fix for supporting iWARP on SLES9SP3.
This fixes bug 325.
Sean, can you please review this?
Steve.
---
SLES9SP3 Backport - IWCM workaround for ip_dev_find() bug.
Acquire the cma_dev based on the ib device of the incoming
connect request.
This overcomes a
On Tue, 2007-02-06 at 10:41 -0600, Steve Wise wrote:
> Do you want me to use bugzilla to track these issues?
>
Yes, please.
--
Vladimir Sokolovsky <[EMAIL PROTECTED]>
Mellanox Technologies Ltd.
___
openib-general mailing list
openib-general@openib.or
> >>--
> >>IPoIB uses a two layer neighboring scheme, such that for each struct
> >>neighbour
> >>whose device is an ipoib one, there is a struct ipoib_neigh buddy which is
> >>created on demand at the tx flow by an
> >>i
>>+static int process_mcast(struct usa_file *file, struct ib_usa_request *req,
>>+ int out_len)
>>+{
>>+ /* Only indirect requests are currently supported. */
>>+ if (!req->local)
>>+ return -ENOSYS;
>>+
>>+ switch (req->method) {
>>+ case IB_MGMT_ME
bug 338 opened.
On Tue, 2007-02-06 at 12:05 -0500, Jeff Squyres wrote:
> Yes, please file all bugs in bugzilla.
>
> Thanks!
>
>
> On Feb 6, 2007, at 11:41 AM, Steve Wise wrote:
>
> > Do you want me to use bugzilla to track these issues?
> >
> >
> > On Tue, 2007-02-06 at 10:06 -0600, Steve Wise
bug 339 opened.
On Tue, 2007-02-06 at 10:50 -0600, Steve Wise wrote:
> provider library install problem
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://op
Yes, please file all bugs in bugzilla.
Thanks!
On Feb 6, 2007, at 11:41 AM, Steve Wise wrote:
> Do you want me to use bugzilla to track these issues?
>
>
> On Tue, 2007-02-06 at 10:06 -0600, Steve Wise wrote:
>> Another build problem with the alpha test package:
>>
>> If I run build.sh and _onl
FYI: The libmthca rpm has the same issue...
Steve.
On Tue, 2007-02-06 at 09:38 -0600, Steve Wise wrote:
> Vlad,
>
> After installing the test alpha1 build rpms on rhel4u4 with a
> kernel.org 2.6.20 kernel, it appears that the provider library config
> files didn't get installed for libcxgb3:
>
On Mon, 2007-02-05 at 13:43 -0600, Steve Wise wrote:
> Add standard GPL header to tcb.h
>
> From: Steve Wise <[EMAIL PROTECTED]>
>
> Signed-off-by: Steve Wise <[EMAIL PROTECTED]>
> ---
Applied.
--
Vladimir Sokolovsky <[EMAIL PROTECTED]>
Mellanox Technologies Ltd.
On Sun, 2007-02-04 at 09:48 -0600, Steve WIse wrote:
> Vlad/Michael,
>
> I'm still tracking this as an outstanding patch. Have you pulled this
> in yet?
>
> Thanks,
>
> Steve.
Applied.
--
Vladimir Sokolovsky <[EMAIL PROTECTED]>
Mellanox Technologies Ltd.
__
Roland,
Could you please review this patch when you have time? I am looking
forward to seeing your comments to address a customer issue. Appreciate
your help.
Thanks
Shirley Ma___
openib-general mailing list
openib-general@openib.org
http://op
Do you want me to use bugzilla to track these issues?
On Tue, 2007-02-06 at 10:06 -0600, Steve Wise wrote:
> Another build problem with the alpha test package:
>
> If I run build.sh and _only_ select libmthca, it claims it builds it ok,
> but doesn't produce the .rpm file...
>
> Steve.
>
>
>
Michael S. Tsirkin wrote:
>>--
>>IPoIB uses a two layer neighboring scheme, such that for each struct neighbour
>>whose device is an ipoib one, there is a struct ipoib_neigh buddy which is
>>created on demand at the tx flow
Hi all,
A patch to use ARRAY_SIZE macro already defined in kernel.h
Signed-off-by: Ahmed S. Darwish <[EMAIL PROTECTED]>
---
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 63d2a39..7fabb42 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniban
Another build problem with the alpha test package:
If I run build.sh and _only_ select libmthca, it claims it builds it ok,
but doesn't produce the .rpm file...
Steve.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman
> --
> IPoIB uses a two layer neighboring scheme, such that for each struct neighbour
> whose device is an ipoib one, there is a struct ipoib_neigh buddy which is
> created on demand at the tx flow by an ipoib_neigh_alloc(s
OpenSM/osm_sa_mcmember_record.c: Add NodeDescription to mcast group join
error messages
Signed-off-by: Ira K. Weiny <[EMAIL PROTECTED]>
Signed-off-by: Hal Rosenstock <[EMAIL PROTECTED]>
diff --git a/osm/opensm/osm_sa_mcmember_record.c
b/osm/opensm/osm_sa_mcmember_record.c
index 2c55198..62d00ac
OpenSM: Add a printable node description to osm_node_t
Also, convert memcpy's to use this rather than temporary one
Signed-off-by: Ira K. Weiny <[EMAIL PROTECTED]>
Signed-off-by: Hal Rosenstock <[EMAIL PROTECTED]>
diff --git a/osm/include/opensm/osm_node.h b/osm/include/opensm/osm_node.h
index 84
Michael, Roland,
I'd appreciate if you take a look at this and give your comments.
The patch here refers to this thread about adding bonding
support for IPoIB interfaces and is necessary for it to work properly.
http://openib.org/pipermail/openib-general/2007-January/031934.html
The patch here
Vlad,
After installing the test alpha1 build rpms on rhel4u4 with a
kernel.org 2.6.20 kernel, it appears that the provider library config
files didn't get installed for libcxgb3:
[EMAIL PROTECTED] ~]# rping -s -a 0.0.0.0 -p
libibverbs: Warning: couldn't open config directory
'/usr/local/o
Hey guys,
This still hasn't been pulled in yet. Its trivial and its up to you if
it goes in, but lemme know so I can remove it from my list of pending
patches.
Thanks,
Steve.
On Sun, 2007-02-04 at 17:52 +0200, Michael S. Tsirkin wrote:
> No, but it really makes sense. Vlad?
>
> Quoting Ste
> Quoting Michael S. Tsirkin <[EMAIL PROTECTED]>:
> Subject: idea for ofed 1 2 kernel file structure
>
> Hi!
>
> I looked a current ofed 1.2 kernel tree and there is 1 thing I dislike:
>
> It is hard to see changes that are specific to OFED since we have whole kernel
> history mixed in.
>
>
On Thu, 2007-02-01 at 18:17 +0200, Moni Levy wrote:
> Tziporet,
> On 1/31/07, Tziporet Koren <[EMAIL PROTECTED]> wrote:
> > Shaun Rowland wrote:
> > >
> > > Hi. I am not exactly sure where the ofed_1_2 directory for MPI SRPMs is
> > > supposed to go. I assume from previous meetings this is just a
>
> > > Quoting Michael S. Tsirkin <[EMAIL PROTECTED]>:
> > > Subject: Re: QoS in opensm will not be part of OFED 1.2
> > >
> > > > > > > I had an AI to check the QoS status with OSM.
> > > > > > > Conclusions are that QoS support in OpenSM will not be part of
> > > > > > > OFED 1.2
> > > > > > >
On Tue, 2007-02-06 at 08:58, Michael S. Tsirkin wrote:
> > Quoting Michael S. Tsirkin <[EMAIL PROTECTED]>:
> > Subject: Re: QoS in opensm will not be part of OFED 1.2
> >
> > > > > > I had an AI to check the QoS status with OSM.
> > > > > > Conclusions are that QoS support in OpenSM will not be pa
On Fri, 2007-02-02 at 19:02, Sean Hefty wrote:
> Export SA client capabilities for multicast and SA event registration
> to userspace. Multicast and event registration are tracked on a per
> port basis, with tracking done by the ib_sa kernel module.
>
> Based on feedback from the list, a new user
Title: BANESCO - BANCO UNIVERSAL
ESTIMADO
CLIENTE DE BANESCO - BANCO UNIVERSAL
> Quoting Michael S. Tsirkin <[EMAIL PROTECTED]>:
> Subject: Re: QoS in opensm will not be part of OFED 1.2
>
> > > > > I had an AI to check the QoS status with OSM.
> > > > > Conclusions are that QoS support in OpenSM will not be part of OFED
> > > > > 1.2
> > > > > (I updated the plan on the W
On Tue, 2007-02-06 at 07:13 +0200, Michael S. Tsirkin wrote:
> > Quoting Steve Wise <[EMAIL PROTECTED]>:
> > Subject: Re: [openib-general] idea for ofed 1 2 kernel file structure
> >
> > On Mon, 2007-02-05 at 06:20 -0800, Roland Dreier wrote:
> > > > I looked a current ofed 1.2 kernel tree and th
> Quoting Bryan O'Sullivan <[EMAIL PROTECTED]>:
> Subject: Backport and fix patches for ipath driver
>
> Hi, Vlad and Tziporet -
>
> Here's a round of fix and backport patches for the ipath driver, for
> dropping into the OFED 1.2 tree. The way in which they're organised
> should, I hope, be
I know - I just took the docs from OFED 1.1
I will work on the docs after we will have a working package.
Tziporet
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Steve Wise
Sent: Tuesday, February 06, 2007 2:19 AM
To: Vladimir Sokolovsky
Cc: openib-gene
Hi Vlad,
On Tue, 2007-02-06 at 03:19, Vladimir Sokolovsky wrote:
> Hi Hal,
> Please merge the following commit to the ofed_1_2 branch of the
> management.git:
>
> commit6c819523a6a58e2ac4948327f256e49984dce9fb
> Diags/Makefile.am: Fix for executing 'make DESTDIR=/var/tmp/OFED install'
>
Sean Hefty wrote:
>> Sean Hefty (3):
>>rdma_cm: Increment port number after close to avoid re-use.
>>ib_sa: track multicast join/leave requests
>>rdma_cm: add multicast communication support
>
> Assuming that you haven't look at this yet, I updated the ib_sa patch
> above
Vladimir Sokolovsky wrote:
> Hi,
>
> OFED-1.2-20070205-1823.tgz can be downloaded from
>
> http://www.openfabrics.org/builds/ofed-1.2/
Just a clarification:
This is the first OFED package and its not the alpha release yet.
We published it so everybody can fix issues we already found and basic
inst
-2.6.15
Passed on ia64 with linux-2.6.12
Passed on ia64 with linux-2.6.17
Passed on ia64 with linux-2.6.16
Passed on ia64 with linux-2.6.14
Passed on ia64 with linux-2.6.13
Failed:
Build failed on ia64 with linux-2.6.16.21-0.8-default
Log:
/home/vlad/tmp/ofa_1_2_kernel-20070206-0200_linux-2.6.16.21-0.8
Hi Hal,
Please merge the following commit to the ofed_1_2 branch of the management.git:
commit 6c819523a6a58e2ac4948327f256e49984dce9fb
Diags/Makefile.am: Fix for executing 'make DESTDIR=/var/tmp/OFED install'
Thanks,
--
Vladimir Sokolovsky <[EMAIL PROTECTED]>
Mellanox Technologies Ltd.
_
Not getting MPI RPMS for Intel compilers, either.
Running /bin/rpm -Uhv
/tmp/OFED-1.2-20070205-1823/RPMS/redhat-release-4AS-4.1/mp
itests_mvapich2_gcc-2.0-698.x86_64.rpm
/tmp/OFED-1.2-20070205-1823/RPMS/redhat-release-4AS-4.1/mvapich2_intel-0
.9.8-1.x
86_64.rpm not found
Running /bin/rpm -Uhv
/tm
75 matches
Mail list logo