From: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
To: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: linux-rdma <linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
OpenFabrics EWG <ewg-G2znmakfqn7U1rindQTSdQ@public.gmane.org>,
Jeff Squyres <jsquyres-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>
Subject: Re: bug 1918 - openmpi broken due to rdma-cm changes
Date: Thu, 04 Feb 2010 16:39:23 -0600 [thread overview]
Message-ID: <4B6B4C9B.8070804@opengridcomputing.com> (raw)
In-Reply-To: <DE586AB7003E4FC4B3850004A0B3CAF6-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
Sean Hefty wrote:
>> OpenMPI uses rdma_bind_addr() to figure out which ip addresses are valid
>> for which IB devices. This logic is now broken. Regardless of whether
>> OpenMPI should use another method for determining which IP address
>> belong to which interfaces, we should probably rethink whether we're
>> breaking rdma-cm semantics in a bad way on a point release.
>>
>
> The changes to the rdma_cm have been merged upstream. These were fixes
> specifically to enable using the loopback address with RDMA devices.
>
> At first thought, we can extend enum ib_device_cap_flags to indicate if a device
> supports loopback capabilities or not. The rdma_cm could then skip over such
> devices when dealing with a loopback address.
>
> - Sean
>
But how can you determine _which_ rdma device should be used if and app
binds to 127.0.0.1? I think this is busted...
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2010-02-04 22:39 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <4B6B47D0.9030507@aoot.com>
[not found] ` <4B6B47D0.9030507-10udUCx4aRo@public.gmane.org>
2010-02-04 22:33 ` bug 1918 - openmpi broken due to rdma-cm changes Sean Hefty
[not found] ` <DE586AB7003E4FC4B3850004A0B3CAF6-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-04 22:39 ` Steve Wise [this message]
[not found] ` <4B6B4C9B.8070804-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-04 22:42 ` Sean Hefty
[not found] ` <EEF75E01C32544C688989E66FECDC422-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-04 22:49 ` Steve Wise
[not found] ` <4B6B4EFE.3010205-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-04 22:54 ` Sean Hefty
[not found] ` <DB361897EE7C40C5AB494AAC2D8625AC-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-04 23:04 ` Steve Wise
[not found] ` <4B6B5277.80307-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-04 23:35 ` Roland Dreier
[not found] ` <aday6j8efqs.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-02-04 23:44 ` Steve Wise
[not found] ` <4B6B5BD7.9090301-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-04 23:50 ` Roland Dreier
[not found] ` <adatytwef1i.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-02-05 0:03 ` Paul Grun
2010-02-04 22:55 ` Steve Wise
[not found] ` <4B6B5048.5020707-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-04 22:56 ` Sean Hefty
2010-02-05 11:32 Jeff Squyres (jsquyres)
[not found] ` <58D723FE08DC6A4398E6596E38F3FA170566DA-2KNrN6/GZtCAsgjym8flbKBKnGwkPULj@public.gmane.org>
2010-02-05 16:16 ` Steve Wise
[not found] ` <4B6C4460.3050908-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-05 16:45 ` Steve Wise
2010-02-05 17:51 ` Roland Dreier
[not found] ` <ada4olvefl4.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-02-05 17:58 ` Jeff Squyres
[not found] ` <324EFA68-12F6-46E9-B876-7F4847B53224-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>
2010-02-05 18:32 ` Steve Wise
[not found] ` <4B6C6453.9090706-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-05 18:49 ` Roland Dreier
2010-02-05 18:56 ` Jason Gunthorpe
[not found] ` <20100205185616.GS16490-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2010-02-05 20:08 ` Jeff Squyres
[not found] ` <E8FF8BD1-80AC-4AA7-BC2A-CE7547FB9ABA-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>
2010-02-05 21:14 ` Jason Gunthorpe
[not found] ` <20100205211455.GT16490-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2010-02-05 21:40 ` Jeff Squyres
[not found] ` <697C6107-13A9-48E3-B451-02529305100D-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>
2010-02-05 21:53 ` Steve Wise
[not found] ` <4B6C9369.1070208-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-05 22:15 ` Sean Hefty
[not found] ` <77E29960440B4806B112A7158F4FA1C4-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-05 22:21 ` Steve Wise
2010-02-06 16:18 ` Steve Wise
2010-02-05 22:20 ` Jeff Squyres
2010-02-06 0:54 ` Roland Dreier
2010-02-05 18:42 ` Sean Hefty
[not found] ` <3762D25FD9474444A4B3E2240EFB8D0E-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-05 19:01 ` Steve Wise
[not found] ` <4B6C6B23.4010704-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-05 19:24 ` Roland Dreier
2010-02-05 17:57 ` Jeff Squyres
2010-02-05 16:22 ` Sean Hefty
[not found] ` <0D5487526204477AA2ABED06E46768E2-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-05 16:38 ` Steve Wise
[not found] ` <4B6C498F.3060708-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-05 16:52 ` Sean Hefty
[not found] ` <F6DF49B759AD49EEB44BECD99FE26DCF-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-05 17:08 ` Steve Wise
2010-02-05 20:09 ` Sean Hefty
[not found] ` <38B735478FE94F40BBA3E8BFD794B10F-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-06 16:31 ` Steve Wise
[not found] ` <4B6D9948.6040007-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-02-06 16:45 ` Steve Wise
2010-02-07 0:12 ` Sean Hefty
[not found] ` <B41CA82E76BB439B892B4874D38EA652-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-02-07 1:22 ` Steve Wise
2010-02-07 11:56 ` [ewg] " Tziporet Koren
2010-02-07 16:39 ` Steve Wise
2010-02-07 16:48 ` Roland Dreier
[not found] ` <ada4oltxa8j.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-02-07 17:42 ` Steve Wise
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4B6B4C9B.8070804@opengridcomputing.com \
--to=swise-7bpotxp6k4+p2yhjcf5u+vpxobypeauw@public.gmane.org \
--cc=ewg-G2znmakfqn7U1rindQTSdQ@public.gmane.org \
--cc=jsquyres-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox