Hi Hal,
Sorry for being ambiguous on the answers below. However, I figured out what the
problem was (while not looking at the code and thinking over it offline.) The
main mistake was the umad_send part in the while(1) loop. Where I have
specified the timeout value greater than '0' which means
Hi Abhijit,
On Thu, 2006-08-10 at 10:55, Abhijit Gadgil wrote:
> Hi Hal,
> I tried using the umad code as per the latest repository.
> (The latest fix is on libibumad/umad.c Line # 806 right?)
Yes.
> I manually applied that patch.
OK but not sure why you did this "manually".
> It doesn't s
Hi,
I have found out
that dapl_rmr_create() function will never succeed in current gen-2 uDAPL
implementation since dapls_ib_mw_alloc() function is not implemented. What is
the reason for this ? Does it mean that DAPL doesn't support RDMA operations
?
Thanks,
Boris Shpolyansky
Applica
On Thu, 2006-08-10 at 16:59, Roland Dreier wrote:
> James> Why don't you find it useful as an InfiniBand diagnosis
> James> tool?
>
> James> In the absence of IPoIB (and therefore ICMP pings), it can
> James> be used to test connectivity.
>
> Sure, but AFAIK the ibping userspace a
On Thu, 2006-08-10 at 16:36, James Lentini wrote:
> On Thu, 10 Aug 2006, Ira Weiny wrote:
>
> > Is there a reason ib_ping.ko is not in this release?
>
> The OFED release team decided to only pull kernel sources from the
> upstream kernel.
There are some things which have not yet gone upstream
James> Why don't you find it useful as an InfiniBand diagnosis
James> tool?
James> In the absence of IPoIB (and therefore ICMP pings), it can
James> be used to test connectivity.
Sure, but AFAIK the ibping userspace app (which is required to use it
anyway) has a server mode, so yo
On Thu, 10 Aug 2006, Roland Dreier wrote:
> James> Roland, will ib_ping be moving upstream?
>
> No one has submitted it. And I really question what the point of it
> is anyway.
Why don't you find it useful as an InfiniBand diagnosis tool?
In the absence of IPoIB (and therefore ICMP pin
James> Roland, will ib_ping be moving upstream?
No one has submitted it. And I really question what the point of it
is anyway.
- R.
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To un
On Thu, 10 Aug 2006, Ira Weiny wrote:
> Is there a reason ib_ping.ko is not in this release?
The OFED release team decided to only pull kernel sources from the
upstream kernel.
I understand why they did this, but I too had hoped that ib_ping would
be in the next OFED release.
Roland, will
I have been given OF
bugzilla admin privs, and have added more values.
Scott Weitzenkamp
SQA and Release Manager
Server Virtualization Business
Unit
Cisco Systems
___
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman
[EMAIL PROTECTED] wrote:
> Quoting r. Tom Tucker <[EMAIL PROTECTED]>:
>> Subject: RDMA_READ SGE
>>
>> Roland:
>>
>> iWARP RNIC's have a different SGE limit for RDMA_READ response then
>> they do for other SGE. To support iWARP, we need to add a
>> max_read_sge attribute to the ib_device structure
Quoting r. Tom Tucker <[EMAIL PROTECTED]>:
> Subject: RDMA_READ SGE
>
> Roland:
>
> iWARP RNIC's have a different SGE limit for RDMA_READ response then they
> do for other SGE. To support iWARP, we need to add a max_read_sge
> attribute to the ib_device structure. We had originally mapped this to
On 11:33 Thu 10 Aug , Roland Dreier wrote:
> Sasha> This works like SVK mirroring (I guess it based on the same
> Sasha> SVN::Mirror). It is able preserve history, but may change
> Sasha> revision numbers - mirrored tree is similar but not
> Sasha> equivalent. Will try to play
Sasha> This works like SVK mirroring (I guess it based on the same
Sasha> SVN::Mirror). It is able preserve history, but may change
Sasha> revision numbers - mirrored tree is similar but not
Sasha> equivalent. Will try to play anyway...
If you really care about revision numbers I
On 15:05 Wed 09 Aug , Roland Dreier wrote:
> search for svn-mirror
This works like SVK mirroring (I guess it based on the same SVN::Mirror).
It is able preserve history, but may change revision numbers - mirrored
tree is similar but not equivalent. Will try to play anyway...
Thanks,
Sasha
__
>I think I agree with Michael that having ib_sa_register_client()
>allocate the structure is going to far in the name of encapsulation.
>How about making the structure public, but providing a macro
>DEFINE_IB_SA_CLIENT() to wrap up the initialization? (Similar to
>DEFINE_MUTEX, DEFINE_IDR, etc)
C
Looks safe enough but I'd rather not tinker with locking so late in
the 2.6.18 cycle. The race is purely theoretical at this point, and
these sorts of changes have a tendency to introduce unintended
consequences. So I queued this for 2.6.19 and checke it into svn.
- R.
Tom> Do you want me to submit a patch on top of Steve's, or do you
Tom> want me to wait until you've got the git tree built?
Go ahead and send it, which the caveat that you should keep track of
it and make sure I get it into my git tree...
- R.
_
I think I agree with Michael that having ib_sa_register_client()
allocate the structure is going to far in the name of encapsulation.
How about making the structure public, but providing a macro
DEFINE_IB_SA_CLIENT() to wrap up the initialization? (Similar to
DEFINE_MUTEX, DEFINE_IDR, etc)
For de
Similarly I just checked this in:
(BTW Muli -- I think anonymous enum is better than define because it
lets the compiler have human-readable names for values, rather than
throwing the info away at the preprocessor stage -- so error messages
can be better, etc)
commit e54b82d739d4a2ef992976c8c0692
I fixed this in a slightly different way that seemed cleaner to me
(see below). Please verify that my fix works for you.
Thanks,
Roland
Index: libmthca/src/qp.c
===
--- libmthca/src/qp.c (revision 8875)
+++ libmthca/src/qp.c (
Is there a reason ib_ping.ko is not in this release?
Ira
On Thu, 10 Aug 2006 17:22:07 +0300
"Tziporet Koren" <[EMAIL PROTECTED]> wrote:
> of course I meant slips (we are all awake here :-)
>
>
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Tzip
Roland:
iWARP RNIC's have a different SGE limit for RDMA_READ response then they
do for other SGE. To support iWARP, we need to add a max_read_sge
attribute to the ib_device structure. We had originally mapped this to
max_sge_rd, but someone pointed out that this is not for RDMA_READ in
general, b
Tziporet Koren wrote:
>You are correct - we forgot about it.
>Will be fixed in rc2
>Can you open a bug in bugzilla for the installer package so we will not
>miss it this time?
>
>
>
Done. Bug 195.
___
openib-general mailing list
openib-general@openib.
Manpreet> Hi, Some time ago, I thought there were some thoughts
Manpreet> about making the outstanding RDMA count to be
Manpreet> configurable via a patch to the mthca driver (the
Manpreet> 'rdb_per_qp' parameter in mthca_main.c).
Manpreet> Just curious if the patch was going t
I know at one point
Oracle supported AIO SDP on Linux, is still still supported?
Scott Weitzenkamp
SQA and Release Manager
Server Virtualization Business
Unit
Cisco Systems
___
openib-general mailing list
openib-general@openib.org
http://openib.o
Hi Hal,
I tried using the umad code as per the latest repository. (The latest fix is on
libibumad/umad.c Line # 806 right?) I manually applied that patch. It doesn't
seem to work yet.
Infact, what I figured out was that the 'poll' on the umad->fd isn't blocking
either.
The read returns the
Hi again Abhijit,
On Thu, 2006-08-10 at 09:46, Abhijit Gadgil wrote:
> Hi Hal,
>
> Please see below.
>
> On Aug 10, 2006 07:01 PM, Hal Rosenstock <[EMAIL PROTECTED]> wrote:
>
> > Hi Abhijit,
> >
> > On Thu, 2006-08-10 at 07:21, Abhijit Gadgil wrote:
> > > Hi All,
> > >
> > > I am trying to
of course I meant slips (we are all awake here :-)
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Tziporet Koren
Sent: Thursday, August 10, 2006 4:42 PM
To: Hal Rosenstock
Cc: OpenFabricsEWG; openib
Subject: Re: [openfabrics-ewg] OFED 1.1-rc1 is availab
Hi Hal,
Please see below.
On Aug 10, 2006 07:01 PM, Hal Rosenstock <[EMAIL PROTECTED]> wrote:
> Hi Abhijit,
>
> On Thu, 2006-08-10 at 07:21, Abhijit Gadgil wrote:
> > Hi All,
> >
> > I am trying to write a simple program using libibumad to 'subscribe' for
> > traps and then receive traps f
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of yipee
> Sent: Thursday, August 10, 2006 7:07 AM
> To: openib-general@openib.org
> Subject: Re: [openib-general] HCA not recognized by OFED
>
> Cain, Brian (GE Healthcare ge.com> writes:
> [snip]
>
>
The schedule is sleeps in 2 weeks meaning:
Target release date: 12-Sep
Intermediate milestones:
1. Create 1.1 branch of user level: 27-Jul - done
2. RC1: 8-Aug - done
3. Feature freeze (RC2): 17-Aug
4. Code freeze (rc-x): 6-Sep
5. Final release: 12-Sep
Tziporet
-Original Message-
Fr
Hi Abhijit,
On Thu, 2006-08-10 at 07:21, Abhijit Gadgil wrote:
> Hi All,
>
> I am trying to write a simple program using libibumad to 'subscribe' for
> traps and then receive traps from the SA. Most of the things seem to work
> fine, however I am facing a small problem where, after first read
Cain, Brian (GE Healthcare ge.com> writes:
[snip]
> I suppose I snipped a little too much when I posted the output of lspci.
> It does look just as you indicate: "[InfiniHost III Lx HCA Flash
> Recovery]".
What's this "Flash Recovery" in your lspci output? sounds like you should reburn
the hca w
Hi All,
I am trying to write a simple program using libibumad to 'subscribe' for traps
and then receive traps from the SA. Most of the things seem to work fine,
however I am facing a small problem where, after first read for the trap, all
subsequent reads are not blocking (and return some inco
You are correct - we forgot about it.
Will be fixed in rc2
Can you open a bug in bugzilla for the installer package so we will not
miss it this time?
Thanks,
Tziporet
-Original Message-
From: Arlin Davis [mailto:[EMAIL PROTECTED]
Sent: Thursday, August 10, 2006 12:26 AM
To: Tziporet Kor
36 matches
Mail list logo
