Sean,
our application is using OFED 1.1 under SLES10.
It is a point to point IB connection from a high speed image scanner to a
workstation.
The application is out in the market for about a year.
Now I get complains from the field that they do have dead pthreads hanging
around that are
This email was generated automatically, please do not reply
git_url: git://git.openfabrics.org/ofed_1_2/linux-2.6.git
git_branch: ofed_1_2
Common build parameters: --with-ipoib-mod --with-sdp-mod --with-srp-mod
--with-user_mad-mod --with-user_access-mod --with-mthca-mod --with-core-mod
At long last amount you can smile about.
DiscountPharmacy a Highest Canadian Worldwide Medicine Treatment Assistance
Seller. From the time of opening in March of 2000, Discount-Pharmacy has
earned many drugstore authorizations and turn into one of the mainly safety
pharmaceutical on the World
From: Hoang-Nam Nguyen hnguyen at de.ibm.com
Date: Thu, 2 Aug 2007 10:08:30 +0200
Subject: [PATCH] ehca: map 4k firmware context of cq, qp to user space
This patch utilizes remap_4k_pfn() as introduced by Paul M.,
for details see http://patchwork.ozlabs.org/linuxppc/patch?id=10281,
to map ehca cq,
-2.6.9-55.ELsmp
Passed on x86_64 with linux-2.6.9-22.ELsmp
Passed on x86_64 with linux-2.6.9-34.ELsmp
Passed on ia64 with linux-2.6.16.21-0.8-default
Passed on ppc64 with linux-2.6.18-8.el5
Failed:
Build failed on powerpc with linux-2.6.18
Log:
/home/vlad/tmp/ofa_1_2_c_kernel-20070802-0201_linux
Sean Hefty wrote:
Indeed. The argument I was trying to make is that arp cache
invalidation requires IPoIB PR cache invalidation, this handles 100%
of the cases, including the 10% not covered by doing cache
invalidation based only on IB events such as port up / sm lid change
/ sm reregister
(Request For Help)
Hi,
On the same topic that I wrote about earlier, I put debugs
in my code to store all skbs in bufferA when enqueing multiple
skbs, and store all skbs to bufferB just before doing post.
During post, I compare the two buffers to make sure that I am
not posting in the wrong
attachment: irauu.gif___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Hi Sasha.
This patch removes trailing blanks in bunch of files
Signed-off-by: Yevgeny Kliteynik [EMAIL PROTECTED]
---
infiniband-diags/configure.in |2 +-
libibcommon/Makefile.am |2 +-
libibmad/Makefile.am |2 +-
opensm/Makefile.am|4 ++--
Sean Hefty wrote:
Consider NFS and NFS-RDMA. The NFS gurus struggled with this very
issue and concluded that the RDMA service needs to be on a separate
port. Thus they are proposing a new netid/port number for doing RDMA
mounts vs TCP/UDP mounts. IMO that is the correct way to go: RDMA
On Thursday 02 August 2007, Hoang-Nam Nguyen wrote:
+#ifdef CONFIG_PPC_64K_PAGES
+ /* make sure we map only 4k for fw context */
+ ret = remap_4k_pfn(vma, vma-vm_start, physical EHCA_PAGESHIFT,
+ vma-vm_page_prot);
+#else
ret =
When I said requires I meant that I think that it is required, I
agree that the current IPoIB code does not link them together. In the
beginning on this thread Roland commented saying he agree with me, but
since then he did not provide more input to the discussion...
I think Jason said it
In the RFC patch I posted, the socket is _just_ to allow binding to a
port/addr. Its not used for anything else. From the native stack's
perspective, its a TCP socket in the CLOSED state (but bound) I guess.
For RDMA, I think we're somewhere in between binding to an address,
versus mapping
.
--
Failed:
Build failed on powerpc with linux-2.6.18
Log:
/home/vlad/tmp/ofa_1_2_c_kernel-20070802-0201_linux-2.6.18_powerpc_check/drivers/infiniband/hw/ehca/ehca_main.c:831:
error: invalid type argument of ‘-’
/home/vlad/tmp/ofa_1_2_c_kernel-20070802-0201_linux-2.6.18_powerpc_check/drivers/infiniband/hw
=no CHECK_CROSS=no
~swise/git/ofabuild/build_ofa_kernel.sh
mkdir -p /home/swise/tmp/ofa_1_2_c_kernel-20070802-0912
~/tmp/ofa_1_2_c_kernel-20070802-0912 ~/git/ofabuild
git clone -s --bare --reference /home/vlad/scm/ofed_1_2
/home/vlad/ofed_1_2/linux-2.6 .git
git checkout ofed_1_2 ofed_scripts
Quoting Steve Wise [EMAIL PROTECTED]:
Subject: Re: [ofa-general] Re: ofa_1_2_c_kernel 20070802-0201 daily build
status
Also,
Is something broken in the ofed_1_2 branch? I cannot even build against
the local kernel on the ofa server using the ~vlad/ofed_1_2/linux-2.6
repository
Sean Hefty wrote:
In the RFC patch I posted, the socket is _just_ to allow binding to a
port/addr. Its not used for anything else. From the native stack's
perspective, its a TCP socket in the CLOSED state (but bound) I guess.
For RDMA, I think we're somewhere in between binding to an
Michael S. Tsirkin wrote:
Quoting Steve Wise [EMAIL PROTECTED]:
Subject: Re: [ofa-general] Re: ofa_1_2_c_kernel 20070802-0201 daily build status
Also,
Is something broken in the ofed_1_2 branch? I cannot even build against
the local kernel on the ofa server using the ~vlad/ofed_1_2/linux-2.6
I'm havin' a bad day.
Can you all help me?
My normal process is to use the build_ofa_kernel.sh script from the
ofabuild repository to build against all ofed kernels. But that scripts
in the master branch of the ofabuild repository now assumes 1.2.c
because it tries to configure in the
On the same topic that I wrote about earlier, I put debugs
in my code to store all skbs in bufferA when enqueing multiple
skbs, and store all skbs to bufferB just before doing post.
During post, I compare the two buffers to make sure that I am
not posting in the wrong order, and that
/vlad/scripts/ofed_1_2
Quoting Steve Wise [EMAIL PROTECTED]:
Subject: Re: [ewg] Re: [ofa-general] Re: ofa_1_2_c_kernel 20070802-0201 daily
build status
I'm havin' a bad day.
Can you all help me?
My normal process is to use the build_ofa_kernel.sh script from the
ofabuild repository to build
Quoting Roland Dreier [EMAIL PROTECTED]:
Subject: Re: [PATCH V2] IB/mlx4: enable MSI-X by default
mlx4_err(dev, NOP command failed to generate interrupt
(IRQ %d), aborting.\n,
priv-eq_table.eq[MLX4_EQ_ASYNC].irq);
- if
Looke here:
/home/vlad/scripts/ofed_1_2
Quoting Steve Wise [EMAIL PROTECTED]:
Subject: Re: [ewg] Re: [ofa-general] Re: ofa_1_2_c_kernel 20070802-0201 daily
build status
I'm havin' a bad day.
Can you all help me?
My normal process is to use the build_ofa_kernel.sh script from the
ofabuild
A) what PKEY the ib_sa / ib_mad modules for the path query MAD
B) what PKEY is being places in the path record used for the query.
Neither really... just that the double call to ib_find_pkey() in ib_sa
is not needed after this change.
Never mind, I'll fix it up myself.
mlx4_err(dev, NOP command failed to generate interrupt
(IRQ %d), aborting.\n,
priv-eq_table.eq[MLX4_EQ_ASYNC].irq);
-if (dev-flags MLX4_FLAG_MSI_X)
-mlx4_err(dev, Try again with MSI-X disabled.\n);
thanks, I applied this.
___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
For your explanation I’m creating a new pthread for every new attempt to
connect from the workstation to the image scanner.
This will happen only when one does re-power the image scanner while
having a connection established, this might happen often as once a week
to once a month.
The
Sean Hefty wrote:
If I clone from my local system over the net, I _get_ all the branches!
Anybody know why local clones on the ofa build server are not pulling
all the branches?
Maybe I'm abusing git?
It sounds like a different between git versions. Older git versions
brought in remote
Yea, that's it. But how do I checkout the remote branch? The man page
and 'git help' don't even show the -r option...
I think you use the full name. Example:
git checkout origin/ofed_1_2
- Sean
___
general mailing list
Why doesn't MSI-X work? Isn't this BIOS problem?
Most likely not -- I guess there are a few cases on Opteron where the
BIOS needs to enable HT mapping or something like that, but usually
MSI-X fails because of a chipset problem.
- R.
___
general
If I clone from my local system over the net, I _get_ all the branches!
Anybody know why local clones on the ofa build server are not pulling
all the branches?
Maybe I'm abusing git?
It sounds like a different between git versions. Older git versions
brought in remote branches such that
Well, I still think the simplest thing is to make a new netlink
protocol to maintain a cache table in the kernel and then a simple
user space program that uses the user space RMPP interface (and trap
subscription..) to do GetTable queries and uses netlink to groom the
kernel cache. Basically
attachment: raroru.gif___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
thanks, I applied this as 3 separate patches.
___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
by the way, I had to apply this by hand, because it seems gmail is
destroying the whitespace in the patches. I'm not sure if there's any
way to send patches via gmail except as attachments unfortunately.
___
general mailing list
thanks, applied
___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
Roland,
On 8/2/07, Roland Dreier [EMAIL PROTECTED] wrote:
by the way, I had to apply this by hand, because it seems gmail is
destroying the whitespace in the patches. I'm not sure if there's any
way to send patches via gmail except as attachments unfortunately.
Sorry; I was afraid that was
Sorry; I was afraid that was happening :-( So would attachments be
accepted ? If so, should the change still be sent in text as well ?
Attachments are a pain -- the best is to find a way to send email
without mangling patches. I think you can use a non-web client with
gmail's smtp server to
Hi Sasha,
I am hitting a problem where the user level MAD library seems to be timing
out, causing the ports to be stuck in INIT state because the subnet has no
Master SM available. The system is still in this state, so if there are
any suggestions on what other type of debug info I could collect
On Thu, Aug 02, 2007 at 11:37:27AM -0700, Sean Hefty wrote:
Well, I still think the simplest thing is to make a new netlink
protocol to maintain a cache table in the kernel and then a simple
user space program that uses the user space RMPP interface (and trap
subscription..) to do GetTable
thanks, applied all 3 of your header fixups.
___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
remap_4k_pfn is defined in terms of remap_pfn_range if the base page
size if 4k, so you don't need this #ifdef afaics.
Good point. I'll wait for an updated patch.
___
general mailing list
general@lists.openfabrics.org
thanks, applied.
___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
thanks... I actually applied this for 2.6.24, since it's not really a
fix for anything, and the 2.6.23 window is closed.
___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
To unsubscribe,
Sean Hefty wrote:
Okay - for final patches, I think we want to remove the rdma_cm specific
port spaces, along with changing the API to clarify that it uses the
same port space as TCP/UDP.
If we get rid of the rdma_cm specific port spaces, do we then reduce the
valid possible spaces to
Hi Hal,
Hal Rosenstock wrote:
Hi Yevgeny,
On 7/21/07, Yevgeny Kliteynik [EMAIL PROTECTED] wrote:
Hi All
Please find the attached RFC describing how QoS policy support could be
implemented in the OpenFabrics stack.
Your comments are welcome.
A couple of quick questions:
How does this
If we get rid of the rdma_cm specific port spaces, do we then reduce the
valid possible spaces to just TCP and UDP? Or what? In the sockets
paradigm, the socket is explicitly bound to a protocol space when its
created (based on the protocol id). Do you think we need to change the
Sasha Khapyorsky wrote:
Hi Yevgeny,
On 15:39 Thu 26 Jul , Yevgeny Kliteynik wrote:
* Comments may appear only in a separate line
Why? What is wrong with:
port-name: vs1/HCA-1/P1 # my best port
I can use this too, but then the pound sign, wherever it will
appear, would mean
Hi Roland,
Roland Dreier [EMAIL PROTECTED] wrote on 08/02/2007 09:59:23 PM:
On the same topic that I wrote about earlier, I put debugs
in my code to store all skbs in bufferA when enqueing multiple
skbs, and store all skbs to bufferB just before doing post.
During post, I compare the
Hi Roland,
I did one more test to check the out-of-order theory. I changed my new API
to be:
/* Original code, unmodified */
ipoib_start_xmit()
{
original code
}
/* Added new xmit which is identical to original code but doesn't get the
lock */
ipoib_start_xmit_nolock()
{
original
50 matches
Mail list logo
