Hi Shannon,
The bandwidth figures that you quoted below match with my readings for single port Mellanox DDR HCA (both for unidirection and bidirection). So it seems dual port SDR HCA performs as good as single port DDR HCA. It would help if you can also tell the bandwidth that you got using one
hi roland, ...
On Thu, Oct 05, 2006 at 09:18:36PM -0700, Roland Dreier wrote:
1) the set_multicast_list net device callback
seems to just kick off another thread to do
the work of registering the multicast group.
the mc_list net_device field is only valid
under the netif_tx_lock,
Roland,
This is just an RFC patch (untested).
I'm adding bypass support to a device and have a need to know whenever
an async event is delivered to the consumer. It allows the bypass
library to do WQ or CQ processing that needs to happen when a fatal
async event happens. This async callback
On Fri, 2006-10-06 at 11:17, Arthur Jones wrote:
hi roland, ...
On Thu, Oct 05, 2006 at 09:18:36PM -0700, Roland Dreier wrote:
1) the set_multicast_list net device callback
seems to just kick off another thread to do
the work of registering the multicast group.
the mc_list
Im doing project in Xen+IB and wanted to connect two nodes using the
IB interconnect..
I wanted to know if there is any kind of crossover cable available
which allows me to connect just these 2 nodes without the use of a
switch?
Thanks,
Adit Ranadive
Georgia Institute of Technology,
Atlanta, GA
On Fri, 2006-10-06 at 11:28, Adit Ranadive wrote:
Im doing project in Xen+IB and wanted to connect two nodes using the
IB interconnect..
I wanted to know if there is any kind of crossover cable available
which allows me to connect just these 2 nodes without the use of a
switch?
The same
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Adit Ranadive
Sent: Friday, October 06, 2006 10:29 AM
To: openib-general@openib.org
Subject: [openib-general] Infiniband Crossover Cable
Im doing project in Xen+IB and wanted to connect two nodes
hi hal, ...
On Fri, Oct 06, 2006 at 11:26:26AM -0400, Hal Rosenstock wrote:
[...]
i'm imagining that all the proprietary eth
interfaces + ipoib need to do about the same
thing when it comes to registering with mcast
groups. would you (all) be averse to pulling some
of the mcast group
On Fri, 2006-10-06 at 11:44, Arthur Jones wrote:
hi hal, ...
On Fri, Oct 06, 2006 at 11:26:26AM -0400, Hal Rosenstock wrote:
[...]
i'm imagining that all the proprietary eth
interfaces + ipoib need to do about the same
thing when it comes to registering with mcast
groups. would
Hal Rosenstock wrote:
i didn't know about this work. do you know where i can
find it?
I think it is in svn trunk.
It's in svn. I've create patches against for-2.6.19, and will post that as
part
of a request to merge some on the features upstream.
- Sean
thanks all! i'll have a look...
arthur
On Fri, Oct 06, 2006 at 09:37:39AM -0700, Sean Hefty wrote:
Hal Rosenstock wrote:
i didn't know about this work. do you know where i can
find it?
I think it is in svn trunk.
It's in svn. I've create patches against for-2.6.19, and will post
Off-line someone asked me to clarify my earlier e-mail. Given this
discussion continues, perhaps this might help explain the performance a
bit more. The Max Payload Size quoted here is what is typically
implemented on x86 chipsets though other chipsets may use a larger
value. From a pure
OpenSM: Improve handling of IB router ports
Signed-off-by: Hal Rosenstock [EMAIL PROTECTED]
---
Index: opensm/osm_drop_mgr.c
===
--- opensm/osm_drop_mgr.c (revision 9679)
+++ opensm/osm_drop_mgr.c (working copy)
@@
john t wrote:
Hi Shannon,
The bandwidth figures that you quoted below match with my
readings for single port Mellanox DDR HCA (both for unidirection and
bidirection). So it seems dual port SDR HCA performs as good as single
port DDR HCA. It would help if you can also tell the bandwidth
hi hal, ...
On Fri, Oct 06, 2006 at 11:26:26AM -0400, Hal Rosenstock wrote:
[...]
i'm imagining that all the proprietary eth
interfaces + ipoib need to do about the same
thing when it comes to registering with mcast
groups. would you (all) be averse to pulling some
of the mcast group
On Fri, 2006-10-06 at 15:47, Arthur Jones wrote:
hi hal, ...
On Fri, Oct 06, 2006 at 11:26:26AM -0400, Hal Rosenstock wrote:
[...]
i'm imagining that all the proprietary eth
interfaces + ipoib need to do about the same
thing when it comes to registering with mcast
groups. would
hi hal, ...
On Fri, Oct 06, 2006 at 04:09:05PM -0400, Hal Rosenstock wrote:
On Fri, 2006-10-06 at 15:47, Arthur Jones wrote:
hi hal, ...
On Fri, Oct 06, 2006 at 11:26:26AM -0400, Hal Rosenstock wrote:
[...]
i'm imagining that all the proprietary eth
interfaces + ipoib need to
On 10/5/06, Sean Hefty [EMAIL PROTECTED] wrote:
I'm confused -- how does this fix anything? I don't see any callers
of the new rdma_establish() function ??
This was submitted at the request of Michael and Or, so I'll let them comment.
There are no in tree passive side users of the rdma_cm,
Roland,
Here is another change I need to support kernel bypass in the driver I'm
working on. For this device, the req_notify_cq() operation cannot be
bypassed. Further, the lib needs to pass some info down to the kernel
verb to correctly implement re-arm.
This patch enables passing
On Fri, 2006-10-06 at 17:29 -0500, Steve Wise wrote:
Roland,
Here is another change I need to support kernel bypass in the driver I'm
working on. For this device, the req_notify_cq() operation cannot be
bypassed. Further, the lib needs to pass some info down to the kernel
verb to
As many of you know, we have been in the process of finding a hosting
company that could host the OpenFabrics site along with the SVN/git/?
repository, wiki pages, etc. This has been done and the server is up and
running. It is a dedicated server hosted by johncompanies.com, has
dual-core 3.4GHz
21 matches
Mail list logo
