Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> Subject: Re: [PATH] problem dlopen libibverbs.so
>
> On Thu, Jul 21, 2005 at 01:18:30AM +0300, Michael S. Tsirkin wrote:
> > Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> > > Subject: Re: [PATH] problem dlopen libibverbs.so
> > >
> > > Michael>
On Thu, Jul 21, 2005 at 01:18:30AM +0300, Michael S. Tsirkin wrote:
> Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> > Subject: Re: [PATH] problem dlopen libibverbs.so
> >
> > Michael> I wander if its a better idea to scan the plugin
> > Michael> directory on ibv_get_devices. Seems to me
> From: Libor Michalek [mailto:[EMAIL PROTECTED]
> Sent: Wednesday, July 20, 2005 5:55 PM
>
> On Wed, Jul 20, 2005 at 05:17:09PM -0700, Fab Tillier wrote:
> > > From: Libor Michalek [mailto:[EMAIL PROTECTED]
> > > Sent: Wednesday, July 20, 2005 5:02 PM
> > >
> > > My question is do we really wan
On Wed, Jul 20, 2005 at 05:17:09PM -0700, Fab Tillier wrote:
> > From: Libor Michalek [mailto:[EMAIL PROTECTED]
> > Sent: Wednesday, July 20, 2005 5:02 PM
> >
> > My question is do we really want this, since an application will likely
> > have yet another table containing the app specific connec
> From: Libor Michalek [mailto:[EMAIL PROTECTED]
> Sent: Wednesday, July 20, 2005 5:12 PM
>
> On Thu, Jun 30, 2005 at 07:01:22PM -0700, Arlin Davis wrote:
> >
> > The uDAPL code is now connecting properly but I am having difficulty
> > setting the QP states properly without the ib_cm_init_qp_attr(
> From: Libor Michalek [mailto:[EMAIL PROTECTED]
> Sent: Wednesday, July 20, 2005 5:02 PM
>
> My question is do we really want this, since an application will likely
> have yet another table containing the app specific connection structure.
> How that table is locked and managed will differ base
On Thu, Jun 30, 2005 at 07:01:22PM -0700, Arlin Davis wrote:
>
> The uDAPL code is now connecting properly but I am having difficulty
> setting the QP states properly without the ib_cm_init_qp_attr() call.
> Any chance of providing this call in uCM?
Sean, To do this I'll need to add a kernel
On Tue, Jul 12, 2005 at 10:20:33PM -0700, Fab Tillier wrote:
> > From: Michael S. Tsirkin [mailto:[EMAIL PROTECTED]
> > Quoting r. Sean Hefty <[EMAIL PROTECTED]>:
> > >
> > > I believe that this is purely a userspace issue. I can't see why
> > > using a mutex wouldn't work, but I believe that get_
On Tue, Jul 12, 2005 at 01:45:43PM -0700, Sean Hefty wrote:
> >> one way to handle this is to have destruction flush events first, then
> >> perform the actual destroy...
> >
> >Right, what I was trying to say in the other thread was: walk the event
> >list and kill events for the id that is destro
On Tue, Jul 12, 2005 at 11:53:06AM -0700, Sean Hefty wrote:
> This fell out of the uCM connection ID discussion...
>
> There's an issue reporting events to userspace clients for an object that
> a user may have destroyed. The problem exists with user verbs, but is
> much more likely to be seen by
On Thu, Jul 21, 2005 at 02:40:50AM +0300, Michael S. Tsirkin wrote:
> Quoting r. Libor Michalek <[EMAIL PROTECTED]>:
> > Subject: Re: [PATCH] sdp_conn_put/sdp_conn_hold race
> >
> > On Wed, Jul 20, 2005 at 09:44:18PM +0300, Michael S. Tsirkin wrote:
> > > Quoting r. Michael S. Tsirkin <[EMAIL PROT
Quoting r. Libor Michalek <[EMAIL PROTECTED]>:
> Subject: Re: [PATCH] sdp_conn_put/sdp_conn_hold race
>
> On Wed, Jul 20, 2005 at 09:44:18PM +0300, Michael S. Tsirkin wrote:
> > Quoting r. Michael S. Tsirkin <[EMAIL PROTECTED]>:
> > > The current sdp_conn_put/sdp_conn_hold implementation
> > > see
On Wed, Jul 20, 2005 at 09:44:18PM +0300, Michael S. Tsirkin wrote:
> Quoting r. Michael S. Tsirkin <[EMAIL PROTECTED]>:
> > The current sdp_conn_put/sdp_conn_hold implementation
> > seems to be subject to the following race condition:
>
> Libor, did you have the time to review this patch?
Yes,
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: [PATH] problem dlopen libibverbs.so
>
> Michael> I wander if its a better idea to scan the plugin
> Michael> directory on ibv_get_devices. Seems to me it might be
> Michael> more debuggable for applications if they get error
On Wed, Jul 20, 2005 at 06:45:09PM +0300, Michael S. Tsirkin wrote:
> Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> > > > > What about passing RTLD_GLOBAL to dlopen, instead?
> > > >
> > > > The strange thing is it doesn't work, but it should according to man
> > > > page.
> > >
> > > Better debu
Fix trailing whitespace in sdp_send.c.
Signed-off-by: Michael S. Tsirkin <[EMAIL PROTECTED]>
Index: linux-2.6.12.2/drivers/infiniband/ulp/sdp/sdp_send.c
===
--- linux-2.6.12.2.orig/drivers/infiniband/ulp/sdp/sdp_send.c
+++ linux-2.6.
Quoting r. Michael S. Tsirkin <[EMAIL PROTECTED]>:
> The current sdp_conn_put/sdp_conn_hold implementation
> seems to be subject to the following race condition:
Libor, did you have the time to review this patch?
--
MST
___
openib-general mailing list
Roland Dreier wrote:
Arlin> Hi Roland, I have a question about uverbs
Arlin> cq_events. Currently, uverbs has one event (fd) handle that
Arlin> processes all CQ events. You mentioned earlier that you
Arlin> would possibly add support for more CQ events. Are you
Arlin> thinking one
> "Joe" == Joe Damato <[EMAIL PROTECTED]> writes:
Joe> I am attempting to port some code from gen1 to gen2, has fmr
Joe> been deprecated? What -is- fmr and how does it differ from a
Joe> mr? If I am correct the type struct ib_mr has become struct
Joe> ibv_mr...
FMRs are "fast"
On Wed, Jul 20, 2005 at 06:47:31AM -0400, Hal Rosenstock wrote:
> On Wed, 2005-07-20 at 03:35, Michael S. Tsirkin wrote:
> > Quoting r. Hal Rosenstock <[EMAIL PROTECTED]>:
> > > On Tue, 2005-07-19 at 20:14, Libor Michalek wrote:
> > > > On Wed, Jul 13, 2005 at 07:40:07PM -0400, Hal Rosenstock wrote
Hal Rosenstock wrote:
On Tue, 2005-07-19 at 14:42, Arlin Davis wrote:
Yes, it returns the route data (GID) when the return == 1. However, I
still get a callback event with a req_id ==0 which is somewhat
unexpected. This seems unnecessary given that ib_at_route_by_ip() just
returned the
Title: RE: [openib-general] fmr vs. mr?
From: Joe Damato [mailto:[EMAIL PROTECTED]]
>
> I am attempting to port some code from gen1 to gen2, has fmr
> been deprecated?
fmr is in part of gen2 stack. Look in ib_verbs.h for struct ib_fmr.
-Dror
__
Hello -
I am attempting to port some code from gen1 to gen2, has fmr
been deprecated? What -is- fmr and how does it differ from a mr? If I am
correct the type struct ib_mr has become struct ibv_mr...
Any insight (or information on where I can find more info about
this) is great
Quoting r. Roland Dreier <[EMAIL PROTECTED]>:
> Subject: Re: [PATH] problem dlopen libibverbs.so
>
> Michael> I wander if its a better idea to scan the plugin
> Michael> directory on ibv_get_devices. Seems to me it might be
> Michael> more debuggable for applications if they get error
Michael> I wander if its a better idea to scan the plugin
Michael> directory on ibv_get_devices. Seems to me it might be
Michael> more debuggable for applications if they get error
Michael> messages when they call ibv_get_devices, and not at
Michael> startup: they can step in d
Dotan> why do i need to change the endianess of node_guid when i
Dotan> use it from query_hca?
Which endianess do you want to get the node_guid in?
- R.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinf
Libor> I don't think you can assume that ucm_debug_level will
Libor> always be initialized correctly, or is module_param_named
Libor> clearing it? Otherwise looks fine...
static int foo;
gets put in BSS and is zeroed by the loader.
- R.
Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> > > > What about passing RTLD_GLOBAL to dlopen, instead?
> > >
> > > The strange thing is it doesn't work, but it should according to man
> > > page.
> >
> > Better debug it then.
> >
> It seems that RTLD_GLOBAL doesn't work as expected because libib
On Wed, Jul 20, 2005 at 06:23:49PM +0300, Michael S. Tsirkin wrote:
> Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> > Subject: Re: [PATH] problem dlopen libibverbs.so
> >
> > On Wed, Jul 20, 2005 at 05:57:28PM +0300, Michael S. Tsirkin wrote:
> > > Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> >
Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> Subject: Re: [PATH] problem dlopen libibverbs.so
>
> On Wed, Jul 20, 2005 at 05:57:28PM +0300, Michael S. Tsirkin wrote:
> > Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> > > Subject: Re: [PATH] problem dlopen libibverbs.so
> > >
> > > On Wed, Jul 2
Hi!
With mstflint, you can now use mthca device names, as follows:
./mstflint -d /sys/class/infiniband/mthca0/device/resource0 q
Thanks,
MST
--
MST
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-gene
On Wed, Jul 20, 2005 at 05:57:28PM +0300, Michael S. Tsirkin wrote:
> Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> > Subject: Re: [PATH] problem dlopen libibverbs.so
> >
> > On Wed, Jul 20, 2005 at 05:24:22PM +0300, Michael S. Tsirkin wrote:
> > > Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> >
Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> Subject: Re: [PATH] problem dlopen libibverbs.so
>
> On Wed, Jul 20, 2005 at 05:24:22PM +0300, Michael S. Tsirkin wrote:
> > Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> > > It appears that libmthca relies on back linking to find symbols from
> > >
On Wed, Jul 20, 2005 at 05:24:22PM +0300, Michael S. Tsirkin wrote:
> Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> > It appears that libmthca relies on back linking to find symbols from
> > libibverbs but back linking doesn't work in the later case.
> >
> > I linked libmthca with libibverbs and
Quoting r. Gleb Natapov <[EMAIL PROTECTED]>:
> It appears that libmthca relies on back linking to find symbols from
> libibverbs but back linking doesn't work in the later case.
>
> I linked libmthca with libibverbs and this solved the problem.
I wander, however, what happends if you load libibve
Hello,
There is a problem with ibverbs library if it is not linked with an
application but dynamically loaded by the application in runtime by
dlopen(). It can't load userspace device-specific driver in later case.
Two programs are attached to demonstrate the problem. Compile first one
with:
$ g
ucm library location is /usr/local/lib rather than
/usr/local/lib/infiniband
Signed-off-by: Hal Rosenstock <[EMAIL PROTECTED]>
Index: README
===
--- README (revision 2878)
+++ README (working copy)
@@ -8,7 +8,7 @@
Typicall
On Wed, 2005-07-20 at 07:30, Hal Rosenstock wrote:
> On Tue, 2005-07-19 at 14:42, Arlin Davis wrote:
> > Yes, it returns the route data (GID) when the return == 1. However, I
> > still get a callback event with a req_id ==0 which is somewhat
> > unexpected. This seems unnecessary given that ib_a
On Tue, 2005-07-19 at 14:42, Arlin Davis wrote:
> Yes, it returns the route data (GID) when the return == 1. However, I
> still get a callback event with a req_id ==0 which is somewhat
> unexpected. This seems unnecessary given that ib_at_route_by_ip() just
> returned the data. Is this the expe
On Wed, 2005-07-20 at 03:35, Michael S. Tsirkin wrote:
> Quoting r. Hal Rosenstock <[EMAIL PROTECTED]>:
> > Subject: Re: [PATCHv3] ucm: Only print messages when debug level set
> >
> > On Tue, 2005-07-19 at 20:14, Libor Michalek wrote:
> > > On Wed, Jul 13, 2005 at 07:40:07PM -0400, Hal Rosenstock
On Wed, 2005-07-20 at 04:39, Michael S. Tsirkin wrote:
> Quoting r. amith rajith mamidala <[EMAIL PROTECTED]>:
> > Subject: Re: Error in opening IB cm device
> >
> > Hi,
> >
> > I couldn't find /dev/infiniband in my installation. After adding this
> > manually and doing mknod as you suggested the
Quoting r. amith rajith mamidala <[EMAIL PROTECTED]>:
> Subject: Re: Error in opening IB cm device
>
> Hi,
>
> I couldn't find /dev/infiniband in my installation. After adding this
> manually and doing mknod as you suggested the error in opening the
> /dev/infiniband/ucm disappeared.
You shouldn
On Wed, Jul 20, 2005 at 10:35:07AM +0300, Michael S. Tsirkin wrote:
> Quoting r. Hal Rosenstock <[EMAIL PROTECTED]>:
> > Subject: Re: [PATCHv3] ucm: Only print messages when debug level set
> >
> > On Tue, 2005-07-19 at 20:14, Libor Michalek wrote:
> > > On Wed, Jul 13, 2005 at 07:40:07PM -0400, H
Quoting r. Hal Rosenstock <[EMAIL PROTECTED]>:
> Subject: Re: [PATCHv3] ucm: Only print messages when debug level set
>
> On Tue, 2005-07-19 at 20:14, Libor Michalek wrote:
> > On Wed, Jul 13, 2005 at 07:40:07PM -0400, Hal Rosenstock wrote:
> > > ucm: Only print messages when debug level set
> >
44 matches
Mail list logo