Title: Mailing
It was really great to meet everybody at the workshop. I'm glad I could come.
Thanks to the organizers.
I would like to bring the topic of how we can improve the effectiveness of our mailing interchange:
The openib-general is the mailing list we all share. It covers all the
Hi Ron,
On Mon, 2005-02-14 at 15:59, Ronald G. Minnich wrote:
> formerly working opensm starts to get these:
So the OpenSM was up and running and these messages appeared in the log.
Did anything change in the subnet ?
> [1108414727:000284173][411FF970] -> umad_receiver: send completed with
> er
Hi Ron,
On Mon, 2005-02-14 at 15:59, Ronald G. Minnich wrote:
> formerly working opensm starts to get these:
So the OpenSM was up and running and these messages appeared in the log.
Did anything change in the subnet ?
> [1108414727:000284173][411FF970] -> umad_receiver: send completed with
> er
Hi,
A couple more things on this:
On Tue, 2005-02-15 at 06:50, Hal Rosenstock wrote:
> Hi Ron,
>
> On Mon, 2005-02-14 at 15:59, Ronald G. Minnich wrote:
> > formerly working opensm starts to get these:
>
> So the OpenSM was up and running and these messages appeared in the log.
> Did anything c
On Tue, 15 Feb 2005, Hal Rosenstock wrote:
> ibstatus/ibstat can show the local port logical and physical port state.
bluesteel:~ # ibstat
CA 'mthca0':
CA type: MT23108
Number of ports: 2
Firmware version: 3.3.2
Hardware version: a1
Node GUID: 0x0002c9010
On Tue, 2005-02-15 at 08:53, Ronald G. Minnich wrote:
> On Tue, 15 Feb 2005, Hal Rosenstock wrote:
>
> > ibstatus/ibstat can show the local port logical and physical port state.
>
> bluesteel:~ # ibstat
> CA 'mthca0':
> CA type: MT23108
> Number of ports: 2
> Firmware vers
Eitan> 1. Use more mailing lists (e.g. openib-ib-manegement )
I've always resisted splitting openib-general. I still think it's a
bad idea for several reasons:
- openib-general is still a low-traffic list. linux-kernel works
fine with 10 times the number of messages per day.
- we end u
On Tue, 15 Feb 2005, Roland Dreier wrote:
> Eitan> 1. Use more mailing lists (e.g. openib-ib-manegement )
>
> I've always resisted splitting openib-general. I still think it's a
> bad idea for several reasons:
yes, splitting makes no sense for the volume of this list.
I would hate to see
On Tue, Feb 15, 2005 at 12:16:24PM +0200, Eitan Zahavi wrote:
> As my main interest and contribution is in the area of IB subnet management
> and tools, I had to write email filters that allows me to focus on this area.
> However, these filters are far from perfect and many times I loose
> valuable
>I think the proper fix for those places calling
ipoib_put_ah() inside
a lock is to move the ipoib_ah structs to a temporary list and then
put them outside of the lock.
I will create a new patch.
Thanks
Shirley Ma
IBM Linux Technology Center
15300 SW Koll Parkway
Beaverton, OR 97006-6063
Phone(F
I am planning to use bugzilla to file
bug reports. I logged in but I only see one bug report there. Are we really
using this?
Thanks
Shirley Ma
IBM Linux Technology Center
15300 SW Koll Parkway
Beaverton, OR 97006-6063
Phone(Fax): (503) 578-7638
___
op
This patch matches received messages against local and remote IDs (versus
local ID only). It relocates a structure definition, and fixes a race
receiving a duplicate REQ.
These changes will be needed as part of timewait handling.
Signed-off-by: Sean Hefty <[EMAIL PROTECTED]>
Index: infiniband/c
Eitan Zahavi wrote:
I would like to propose two options to resolve that:
1. Use more mailing lists (e.g. openib-ib-manegement )
2. Use keywords in the mail Subject (e.g. Subject: [SM] I have a problem)
I would rather not have multiple mailing lists. I like that use of
keywords, but I've found tha
Sean> I would rather not have multiple mailing lists. I like that
Sean> use of keywords, but I've found that threads frequently
Sean> change topics.
Is this really a big problem anyway? If the list gets 40 mails a day
(which is a busy day) and it takes 15 seconds (which is generous)
Hello folks,
I'm sorry if this is kind of off-topic for this list but I suspect that there
are quite a few people on this list that can answer my rather simple
question.
Every time the tavor-driver loads I see these (kinda scary) warnings:
THH kernel module initialized successfully VAPI(2): th
Hi,
Unfortunately, the Solaris 10 IPoIB MTU with OpenSM is back to the
maximum size of 252 again :-( I'm not sure whether this was ever really
fixed although I do now see the packets indicating an exact MTU of 4
(2048 bytes). I'm not sure what Solaris doesn't like about the OpenSM
response to the
Roland Wrote,
>Is this really a big problem anyway? If the list gets 40 mails a day
>(which is a busy day) and it takes 15 seconds (which is generous) to
>glance at a mail and decide if you're interested, you're only spending
>10 minutes a day looking at mail.
> - R.
I agree with Roland, I thi
Woodruff, Robert J wrote:
Roland Wrote,
Is this really a big problem anyway? If the list gets 40 mails a day
(which is a busy day) and it takes 15 seconds (which is generous) to
glance at a mail and decide if you're interested, you're only spending
10 minutes a day looking at mail.
I agree with
> -Original Message-
> > Roland Wrote,
> >
> >
> >>Is this really a big problem anyway? If the list gets 40 mails a day
> >>(which is a busy day) and it takes 15 seconds (which is generous) to
> >>glance at a mail and decide if you're interested, you're only spending
> >>10 minutes a da
I have a hunch for whats happening here, but before I jump into any
conclusions, I am seeing some other issue between Solaris IPoIB driver
and OpenSM. After joining the Broadcast group, the PathRecord Response
coming from OpenSM signals an error with Invalid GUID. I wonder why,
Here is the mad trac
On Tue, 2005-02-15 at 16:36, Nitin Hande wrote:
> I have a hunch for whats happening here,
Glad to hear this as I don't have a clue :-)
> but before I jump into any
> conclusions, I am seeing some other issue between Solaris IPoIB driver
> and OpenSM. After joining the Broadcast group, the PathR
Hi again Nitin,
On Tue, 2005-02-15 at 16:36, Nitin Hande wrote:
> After joining the Broadcast group, the PathRecord Response
> coming from OpenSM signals an error with Invalid GUID. I wonder why,
There appear to be only 2 places in the code (I'm not saying the code is
right) where this can occur.
Hi Nitin,
On Tue, 2005-02-15 at 16:45, Hal Rosenstock wrote:
> Can you look in the osm.log to see if the source or dest GID is
> implicated ? This will help me chase it down. Thanks.
Both SGID and DGID are in the component mask but my bet is on the DGID.
OpenSM does not currently support PathReco
On Tue, 2005-02-15 at 13:45, Hal Rosenstock wrote:
> Hi again Nitin,
>
> On Tue, 2005-02-15 at 16:36, Nitin Hande wrote:
> > After joining the Broadcast group, the PathRecord Response
> > coming from OpenSM signals an error with Invalid GUID. I wonder why,
>
> There appear to be only 2 places in
After discussing it more with folks here, is seems to us that
perhaps for the uDAPL user-mode library, it be provided to
openib.org under a dual BSD + LGPL library rather than a BSD + GPL
since people normally want to use LGPL for libraries.
I'm in favor of what ever licensing scheme our user's
On Mon, Feb 14, 2005 at 02:39:21PM -0800, Tom Duffy wrote:
> On Mon, 2005-02-14 at 14:20 -0800, Libor Michalek wrote:
> > Here's a patch for the print format warning in the debug data path.
>
> OK, good. Thanks. Now clean on x86_64 with data debug on. Still
> seeing these on sparc64:
Tom,
On Tue, 2005-02-15 at 17:45, Nitin Hande wrote:
> Here is the osm log, I think we may have a lead, the dest GID is wrong:
> :
>
> Feb 15 23:29:57 [43005960] -> osm_sm_mcgrp_join: Port 0x0002c901097651d1
> joining MLID 0xC001.
> Feb 15 23:29:57 [43005960] -> __osm_pr_rcv_get_end_points: No dest po
On Tue, 2005-02-15 at 10:08 -0800, Shirley Ma wrote:
>
> I am planning to use bugzilla to file bug reports. I logged in but I
> only see one bug report there. Are we really using this?
I have filed a couple. I won't discourage you using bugzilla, but you
may have quicker response on the list.
On Mon, 2005-02-14 at 16:47 -0800, Woodruff, Robert J wrote:
> Hi Arkady,
>
> As I mentioned in the BOF, I have a person (Arlin Davis) that can help
> with
> developing a uDAPL provider for the openib.org verbs.
> After discussing it more
> with folks here, is seems to us that perhaps for the u
On Tue, 2005-02-15 at 19:48 +0100, Peter KjellstrÃm wrote:
> Hello folks,
>
> I'm sorry if this is kind of off-topic for this list but I suspect that there
> are quite a few people on this list that can answer my rather simple
> question.
>
> Every time the tavor-driver loads I see these (kinda
On Tue, 2005-02-15 at 16:03 -0800, Libor Michalek wrote:
> This patch should clear up all the warnings, can you give it
> a try and let me know if it works.
Perfect. Clean yummy compiles. Thanks.
-tduffy
signature.asc
Description: This is a digitally signed message part
Tom Duffy wrote:
> On Mon, 2005-02-14 at 16:47 -0800, Woodruff, Robert J wrote:
>> Hi Arkady,
>>
>> As I mentioned in the BOF, I have a person (Arlin Davis) that can
>> help with developing a uDAPL provider for the openib.org verbs.
>> After discussing it more
>> with folks here, is seems to us t
On Tue, 2005-02-15 at 15:57, Hal Rosenstock wrote:
> On Tue, 2005-02-15 at 17:45, Nitin Hande wrote:
> > Here is the osm log, I think we may have a lead, the dest GID is wrong:
> > :
> >
> > Feb 15 23:29:57 [43005960] -> osm_sm_mcgrp_join: Port 0x0002c901097651d1
> > joining MLID 0xC001.
> > Feb
On Tue, 2005-02-15 at 09:02 -0800, Roland Dreier wrote:
> Eitan> 1. Use more mailing lists (e.g. openib-ib-manegement )
>
> I've always resisted splitting openib-general. I still think it's a
> bad idea for several reasons:
>
> - openib-general is still a low-traffic list. linux-kernel wor
34 matches
Mail list logo