Can someone please sign me off the mailing list.
The link at the bottom is broken
Regards,
[EMAIL PROTECTED]
http://openib.org/mailman/listinfo/openib-general
Guy Tel-Zur, Ph.D.
http://tel-zur.com
___
general mailing list
general@lists.openfabrics.
> -#define HCA_CAP_MR_PGSIZE_4K 1
> -#define HCA_CAP_MR_PGSIZE_64K 2
> -#define HCA_CAP_MR_PGSIZE_1M 4
> -#define HCA_CAP_MR_PGSIZE_16M 8
> +#define HCA_CAP_MR_PGSIZE_4K 0x8000
> +#define HCA_CAP_MR_PGSIZE_64K 0x4000
> +#define HCA_CAP_MR_PGSIZE_1M 0x2000
> +#define HCA_CAP_
OSM Simulation Regression Summary
[Generated mail - please do NOT reply]
OpenSM binary date = 2007-09-12
OpenSM git rev = Sun_Sep_9_15:57:42_2007
[27f7ec84dbb1060397fa930569bc88d8f6e1d373]
ibutils git rev = Tue_Sep_4_17:57:34_2007
[4bf283f6a0d7c0264c3a1d2de92745e457585fdb]
Total=520 Pa
Hal and Sean, what was the final feeling about this? I seem to recall
some changes were requested? Are there two independent changes mixed
up in one patch here?
> diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
> index 6f42877..9ec910b 100644
> --- a/drivers/infinib
For the week ending Sep 14, you will receive a Contact List for Nursing Homes,
Hospitals and Dentists without charge when you order the Physician Contact List
Licensed Physicians in the USA
788,387 in total 17,400 emails
Coverage in many different areas of medicine such as Endocrinology,
Mixed config should be OK.
Scott
> -Original Message-
> From: Nathan Dauchy [mailto:[EMAIL PROTECTED]
> Sent: Wednesday, September 12, 2007 3:09 PM
> To: Scott Weitzenkamp (sweitzen); general
> Cc: Sufficool, Stanley; Arlin Davis
> Subject: Re: [ofa-general] scp performance over IPoIB
>
On ethernet, I have generally run into problems where mis-matched MTU
settings caused problems. Is this the case on Infiniband?
I would think the issues would be very similar if not exactly the same.
For TCP you are probably OK with different MTUs in the same subnet,
but with UDP sorrow and
Scott Weitzenkamp (sweitzen) wrote:
> What does "cat /sys/class/net/ib0/mode" report? If "datagram", you need
> to run "echo connected > /sys/class/net/ib0/mode", then you can raise
> the MTU.
>
> Scott Weitzenkamp
> SQA and Release Manager
> Server Virtualization Business Unit
> Cisco Systems
What does "cat /sys/class/net/ib0/mode" report? If "datagram", you need
to run "echo connected > /sys/class/net/ib0/mode", then you can raise
the MTU.
Scott Weitzenkamp
SQA and Release Manager
Server Virtualization Business Unit
Cisco Systems
> -Original Message-
> From: [EMAIL PROTEC
How exactly do you set the MTU for ipoib?
I am running the latest unpatched git branch of vofed kernel 1.2.5 and I
get "SIOCSIFMTU: Invalid argument" when I try ifconfig ib0 mtu 65520.
Anything above the preset 2044 returns this issue.
-Original Message-
From: [EMAIL PROTECTED]
[mailto
--- Steve Wise <[EMAIL PROTECTED]> wrote:
>
> >>>
> >> It looks to me like ucma_clean_events() calls
> >> rdma_destroy_id() /
> >> iw_destroy_cm_id() / destroy_cm_id() which calls
> the
> >> provider reject
> >> function. Or NOT! :) There's a comment in the
> >> IW_CM_STATE_CONN_
What happens if someone runs the new driver with older firmware? Or
what if someone upgrades the firmware without updating the driver?
- R.
___
general mailing list
general@lists.openfabrics.org
http://lists.openfabrics.org/cgi-bin/mailman/listinfo/gen
It looks to me like ucma_clean_events() calls
rdma_destroy_id() /
iw_destroy_cm_id() / destroy_cm_id() which calls the
provider reject
function. Or NOT! :) There's a comment in the
IW_CM_STATE_CONN_RECV
case inside destroy_cm_id():
/*
* App ca
--- Steve Wise <[EMAIL PROTECTED]> wrote:
>
>
> Kanoj Sarcar wrote:
> > Response to original mail did not come to me, but
> I
> > see it in the archives, responding back to the
> > archived response. Please reply all on your
> responses.
> >
>
> I did reply to all. My outgoing folder shows t
Kanoj Sarcar wrote:
Response to original mail did not come to me, but I
see it in the archives, responding back to the
archived response. Please reply all on your responses.
I did reply to all. My outgoing folder shows that it went to both of
your addresses...
If the driver detaches th
Response to original mail did not come to me, but I
see it in the archives, responding back to the
archived response. Please reply all on your responses.
If the driver detaches the incoming (child) connection
request from the listener at the point of sending the
IW_CM_EVENT_CONNECT_REQUEST upcall,
Arlin Davis wrote:
Rick Jones wrote:
Davis, Arlin R wrote:
Can someone explain why scp performance over IPoIB would be 10x slower
then on GBE? The netperf numbers look normal.
So, you could try tweaking the MTU on the IPoIB interfaces.
Rick,
Thanks for the suggestion. Looks like we m
>RDMA/CMA: Use neigh_event_send() to initiate neighbour discovery.
>
>Calling arp_send() to initiate neighbour discovery (ND) doesn't do the
>full ND protocol. Namely, it doesn't handle retransmitting the arp
>request if it is dropped. The function neigh_event_send() does all this.
>Without doing
>Did you commit this change to the librdmacm git?
I just pushed this upstream.
Also, here's what I've created so far for the libibcm. I haven't tested
or completed it, but at least it's a starting point. I stopped working
when I reached the event handling code in the libibcm. If you don't get
Davis, Arlin R wrote:
Can someone explain why scp performance over IPoIB would be 10x slower
then on GBE? The netperf numbers look normal.
Might you be running into limitations of the app-level windowing in scp
(ssl?). ISTR there is need of patching to get scp to work "well" with
high bandwi
We can use raw_smp_processor_id() here because the processor ID is only used
for debug output and may therefore be preemption-unsafe.
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]>
---
This is the same patch, but with smp_processor_id() replaced by
raw_smp_processor_id(), as kindly pointed out
On Tuesday 11 September 2007 16:51, Nathan Lynch wrote:
> > - get_paca()->paca_index, __FUNCTION__, \
> > + smp_processor_id(), __FUNCTION__, \
>
> I think I see these macros used in preemptible code (e.g. ehca_probe),
> where smp_processo
From: Hoang-Nam Nguyen <[EMAIL PROTECTED]>
...because, on virtualized hardware like System p, we can't be sure that the
physical pages behind them are contiguous.
Signed-off-by: Joachim Fenkes <[EMAIL PROTECTED]>
---
Another patch for 2.6.24 that will apply cleanly on top of my previous
patchset
Lightning Could Strike Twice!
Yesterday we told you this stock would sky rocket, and today it did!
Moving over 4.1 million shares, and up 100%.
The stock doubled, and is going to double again tomorrow!
There is an odour in the air a huge press release is coming out tomorrow!
ww Energy Inc.
Symbol
Kanoj Sarcar wrote:
Hello iwarp/rdmacm folks,
If an iwarp driver sends a IW_CM_EVENT_CONNECT_REQUEST
type event to the OFA stack, what synchronization (if
any) is provided by OFA against a service destruct
downcall to the driver that will attempt to destroy
the listener for which this upcall w
RDMA/CMA: Use neigh_event_send() to initiate neighbour discovery.
Calling arp_send() to initiate neighbour discovery (ND) doesn't do the
full ND protocol. Namely, it doesn't handle retransmitting the arp
request if it is dropped. The function neigh_event_send() does all this.
Without doing full
/vlad/tmp/ofa_1_3_kernel-20070912-0200_linux-2.6.19_powerpc_check/drivers/infiniband/hw/ehca/ehca_main.c:936:
error: invalid type argument of '->'
/home/vlad/tmp/ofa_1_3_kernel-20070912-0200_linux-2.6.19_powerpc_check/drivers/infiniband/hw/ehca/ehca_main.c:939:
error: invalid typ
Rick,
I have dual core AMD opteron, the IB card are connected to 4X
mellanox infiniscale 2400, I am running Sles 10. when i used to run
the test without any message size (-m )
The SDP test didn't work for me I am try to figure out why also I had
noproblem in loading sdp library.
I also ch
28 matches
Mail list logo
