> -Original Message-
> From: Roland Dreier [mailto:[EMAIL PROTECTED]
> Sent: Thursday, March 31, 2005 8:00 PM
>
> Michael> I dont think so. I found this:
>
> Michael> C9-88: For an HCA responder using Reliable Connection
> Michael> service, for each zero-length RDMA READ or W
David> Roland, netdev@oss.sgi.com CC:'ing either Jeff Garzik and
David> myself, please.
Sorry, will do next time around, unless you'd like me to resend this
batch as well. All 3 patches are pretty trivial, though. The biggest
one is just deleting a lot of code by switching to debugfs.
Michael> I dont think so. I found this:
Michael> C9-88: For an HCA responder using Reliable Connection
Michael> service, for each zero-length RDMA READ or WRITE request,
Michael> the R_Key shall not be validated, even if the request
Michael> includes Immediate data.
Micha
Roland, netdev@oss.sgi.com CC:'ing either Jeff Garzik and
myself, please.
___
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-
From: Hal Rosenstock <[EMAIL PROTECTED]>
Set skb->mac.raw on receive. This fixes crashes when this is
dereferenced, for example by netfilter or when PF_PACKET is used.
Signed-off-by: Hal Rosenstock <[EMAIL PROTECTED]>
Signed-off-by: Roland Dreier <[EMAIL PROTECTED]>
--- linux-export.orig/driver
Ronald> is there a number that this means, i.e. is ifconfig saying
Ronald> "I don't know this number so it is UNSPEC" or is it a
Ronald> number that means "NaN"?
The former. IPoIB reports its (IANA-assigned) link type of 32.
Depending on how new a version you have, "ip addr" will eith
Convert IPoIB to use debugfs instead of its own custom debugging filesystem.
Signed-off-by: Roland Dreier <[EMAIL PROTECTED]>
--- linux-export.orig/drivers/infiniband/ulp/ipoib/ipoib_fs.c 2005-03-31
19:07:14.463965782 -0800
+++ linux-export/drivers/infiniband/ulp/ipoib/ipoib_fs.c2005-0
Correct and simplify calculation of static rate. We need to round up
the quotient of (local_rate - path_rate) / path_rate. To round up we
add (path_rate - 1) to the numerator, so the quotient simplifies to
(local_rate - 1) / path_rate.
No idea how I came up with the old formula.
Signed-off-by:
So far, here are my assumptions regarding the formatting of the RMPP MADs.
The following fields in the RMPP header are set by the user:
Version, Type = DATA, RTime, Flags = ACTIVE, and Status = 0
The RMPP code will set the SegNum and update the Flags, but uses the
ACTIVE bit to determine if the us
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: problem with SDP/AIO on mem-free HCA
>
> [err, resending with a correct openib to: line]
>
> I'm hitting a strange problem with SDP/AIO on a mem-free Arbel. My
> test is the following: I run Libor's ttcp.aio program with default
> paramete
On Wed, 2005-03-30 at 20:04, Josh England wrote:
> Are there any plans to modify the linux DHCP client so it would be
> possible to do kernel-level DHCP and NFSroot over IB?
I took a quick look at this and it looks pretty straightforward. Stay
tuned...
-- Hal
___
FWIW, this is with a 32-bit executable on a 64-bit kernel.
Another weird thing is that SDP seems to be doing two RDMA READs of
size 0x1000 at remote addresses 0x1d94e000 and 0x1d94f000.
With Tavors on a 32-bit machine, the same command line paramters
result in a single RDMA read of size 0x2000.
is there a number that this means, i.e. is ifconfig saying "I don't know
this number so it is UNSPEC" or is it a number that means "NaN"?
thanks
ron
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-ge
On Thu, Mar 31, 2005 at 04:25:28PM -0500, Hal Rosenstock wrote:
> On Wed, 2005-03-30 at 19:43, Libor Michalek wrote:
> > The program has a decent help for available parameters, but here are
> > some reasonable defaults:
> >
> > server:
> >
> > ./ttcp.aio.x -r -l 65536 -a 20
> >
> > clien
On Wed, 2005-03-30 at 19:43, Libor Michalek wrote:
> The program has a decent help for available parameters, but here are
> some reasonable defaults:
>
> server:
>
> ./ttcp.aio.x -r -l 65536 -a 20
>
> client:
>
> ./ttcp.aio.x -t -l 65536 -n 10 -a 20 192.168.0.100
Are these the
[err, resending with a correct openib to: line]
I'm hitting a strange problem with SDP/AIO on a mem-free Arbel. My
test is the following: I run Libor's ttcp.aio program with default
parameters (which I think just leaves one AIO in flight at a time) as
follows:
ttcp.aio.x -r -s &
ttcp.aio.x -t
On Thu, 2005-03-31 at 15:02, Sean Hefty wrote:
> For vendor-specific MADs 0x30-0x4F, does anyone know if the OUI is
> repeated in every RMPP segment? My assumption is that it does, but I
> can't locate a specific statement in the spec that confirms this.
Your assumption is correct.
As those MA
For vendor-specific MADs 0x30-0x4F, does anyone know if the OUI is
repeated in every RMPP segment? My assumption is that it does, but I
can't locate a specific statement in the spec that confirms this.
- Sean
___
openib-general mailing list
openib-gen
> a separate Qos tag is
used for each stream?
Sorry for the late response. You could
do that. I just list some possible uses of Multiple IPoIB devices over
same port. Other reasons could be different MTUs or other interfaces characteristics..
Basically there is no reason to restrict this implemen
On Thu, Mar 31, 2005 at 09:41:59AM -0800, Sean Hefty wrote:
> Hal Rosenstock wrote:
> > Is this just the kmalloc in cm_alloc_msg or is there more to this ?
>
> I _think_ that the kmalloc in cm_alloc_msg is all that needs to change.
Yes, this CM change should be sufficient. I'm testing it now an
Hal Rosenstock wrote:
It seems possible that this is called prior to cm_id_priv->av.port being
initialized. Should an error be returned for this case ?
Can you reference the place in the code where you think that this could
happen? The port should be set before a REQ is sent or immediately
after
ardavis> Has anyone successfully run uverbs examples with events
ardavis> using ibv_get_cq_event? It seems to block forever on my
ardavis> system with the pingpong test.
Yes, I have. I'll try again with the latest code to make sure I
haven't broken anything recently.
- R.
__
On Thu, 2005-03-31 at 12:41, Sean Hefty wrote:
> > It seems possible that this is called prior to cm_id_priv->av.port being
> > initialized. Should an error be returned for this case ?
>
> Can you reference the place in the code where you think that this could
> happen? The port should be set be
Has anyone successfully run uverbs examples with events using
ibv_get_cq_event? It seems to block forever on my system with the
pingpong test.
Thanks,
-arlin
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/o
Hal Rosenstock wrote:
Is this just the kmalloc in cm_alloc_msg or is there more to this ?
I _think_ that the kmalloc in cm_alloc_msg is all that needs to change.
One other comment/question about cm_alloc_msg:
It seems possible that this is called prior to cm_id_priv->av.port being
initialized. Shou
On Tue, 2005-03-29 at 19:05, Sean Hefty wrote:
> Libor Michalek wrote:
>
> >>With this patch, changing the kmalloc in cm_alloc_msg() to use
> >>GFP_ATOMIC rather than GFP_KERNEL should allow the CM to be usable from
> >>interrupt context. Of course, I haven't actually tested this...
> >>
> >>I
أفضل هدية للأطفال وكبار السنالذين
لا يجيدون التعامل مع الكمبيوتر
ريموت كنترول يسهل استخدام والتحكم في
الكمبيوتر (وكأنه فيديو) (فتح وغلق البرامج - تكبير وتصغير الشاشة - رفع وخفض
الصوت - غلق الكمبيوتر - تشغيل ملفات الفيديو - وغيرها...)
مطلوب وكلاء وموزعون في الدول
العربية
اتصل الآن
New Techno
Replace sdp_kmap by kmap_atomic. Use KM_IRQ0 slot, and
disable local interrupts to avoid kmap slot collision.
Incidentially, sdp_iocb.h is now free of stuff not related
to iocb.
Signed-off-by: Michael S. Tsirkin <[EMAIL PROTECTED]>
Index: drivers/infiniband/ulp/sdp/sdp_send.c
Spam detection software, running on the system "openib.ca.sandia.gov", has
identified this incoming email as possible spam. The original message
has been attached to this so you can view it (if it isn't spam) or block
similar future email. If you have any questions, see
[EMAIL PROTECTED] for deta
Hi Scott,
On Thu, 2005-03-31 at 03:49, Scott Bahling wrote:
> What is the general consensus about the Gen1 kernel drivers compared to
> the Gen2 drivers?
The gen2 drivers are faster (more throughput, lower latency) and are
rapidly catching up in functionality. The driver supports both Tavor and
Hello,
We tried contacting you awhile ago about your low interest morta(ge rate.
You have qualified for the lowest rate in years...
You could get over $380,000 for as little as $500 a month!
Ba(d credit? Doesn't matter, low rates are fixed no matter what!
To get a free, no obli,gation c
أفضل هدية للأطفال وكبار السنالذين
لا يجيدون التعامل مع الكمبيوتر
ريموت كنترول يسهل استخدام والتحكم في
الكمبيوتر (وكأنه فيديو) (فتح وغلق البرامج - تكبير وتصغير الشاشة - رفع وخفض
الصوت - غلق الكمبيوتر - تشغيل ملفات الفيديو - وغيرها...)
مطلوب وكلاء وموزعون في الدول
العربية
اتصل الآن
New Techno
Spam detection software, running on the system "openib.ca.sandia.gov", has
identified this incoming email as possible spam. The original message
has been attached to this so you can view it (if it isn't spam) or block
similar future email. If you have any questions, see
[EMAIL PROTECTED] for deta
Hi,
What is the general consensus about the Gen1 kernel drivers compared to
the Gen2 drivers? What is the maturity of the Gen2 code relative to
Gen1, and are there any features in Gen1 missing from Gen2? I am mostly
interested in the kernel module code, but if the Gen2 userspace code is
much bette
34 matches
Mail list logo