public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: sebastien dugue <sebastien.dugue-6ktuUTfB/bM@public.gmane.org>
To: Or Gerlitz <ogerlitz-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
Cc: Roland Dreier <rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>,
	Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
	linux-rdma <linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Roland Dreier <rolandd-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>,
	Sasha Khapyorsky <sashak-smomgflXvOZWk0Htik3J/w@public.gmane.org>
Subject: Re: [PATCH 1/3] rdma_cm: Add support for a new RDMA_PS_LUSTRE Lustre port space
Date: Thu, 21 Jan 2010 09:28:40 +0100	[thread overview]
Message-ID: <20100121092840.7429e81f@frecb007965> (raw)
In-Reply-To: <4B572099.3030604-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>


  Hi Or,

On Wed, 20 Jan 2010 17:26:17 +0200
Or Gerlitz <ogerlitz-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org> wrote:

> sebastien dugue wrote:
> >  No, because in OpenSM's QoS logic, there's no way to map the TCP port
> > space with specific target GUIDs onto an SL. You have keywords for SDP, SRP,
> > RDS, ISER, ... but not for the TCP port space (or am I missing something?).
> 
> going with this, what prevents you from patching opensm qos engine to support
> the lustre service under the tcp port-space and/or support a combination of service 
> and target port-guid? all in all, first, I don't see what a kernel patch buys you
> and second, if it buys you something you should be able to gain the same effect with
> patching open-sm.

  Right, I can indeed achieve that with only a patch to OpenSM. Going with a
specific Lustre port space is simple and less intrusive although you have to
patch the kernel and OpenSM.

  OK, then going with the TCP port space, what we need in OpenSM is a
combination of service id (TCP) _and_ TCP port _and_ target GUID.

  Something like:

  tcp port <lustre TCP port> target-port-guid <Lustre servers GUIDs>

  That way, as you point out, there's absolutely no need for a specific
Lustre specific port space and kernel patch. I just need to extend the
QoS parser logic to add the semantic above.

  I will look into this.

  Thanks, and sorry for the hassle.

  Sebastien.

> 
> thinking on this a bit more, since the rules are processed by order wouldn't the 
> following scheme let you achieve the same effect?
> 
> target-­port­guid 0x1234,0x1235 : 1 # traffic to MDSs
> lustre                        : 2 # default lustre traffic (to OSSs)
> 
> Or.
> 
--
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

  parent reply	other threads:[~2010-01-21  8:28 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-01-13 14:49 [PATCH 0/3] Add support for specific Lustre Qos sebastien dugue
2010-01-13 14:51 ` [PATCH 1/3] rdma_cm: Add support for a new RDMA_PS_LUSTRE Lustre port space sebastien dugue
2010-01-13 16:56   ` Sean Hefty
     [not found]     ` <7ED07283D76C422C9210FBE7C832731B-Zpru7NauK7drdx17CPfAsdBPR1lH4CV8@public.gmane.org>
2010-01-13 17:04       ` Roland Dreier
     [not found]         ` <ada6376ndgs.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-01-14 12:58           ` sebastien dugue
2010-01-14 17:25             ` Roland Dreier
     [not found]               ` <ada3a28mwdw.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-01-15  7:41                 ` sebastien dugue
2010-01-20  1:12                   ` Roland Dreier
     [not found]                     ` <adaiqax37g4.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-01-20  7:55                       ` sebastien dugue
2010-01-20  8:03                         ` Or Gerlitz
     [not found]                           ` <4B56B8E3.3010909-smomgflXvOZWk0Htik3J/w@public.gmane.org>
2010-01-20  9:17                             ` sebastien dugue
2010-01-20 15:26                               ` Or Gerlitz
     [not found]                                 ` <4B572099.3030604-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
2010-01-21  8:28                                   ` sebastien dugue [this message]
2010-01-21  9:12                                     ` Or Gerlitz
     [not found]                                       ` <4B581A68.500-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
2010-01-21  9:26                                         ` sebastien dugue
2010-01-14 12:47       ` sebastien dugue
2010-01-14 14:09         ` Or Gerlitz
     [not found]           ` <4B4F25A7.6000900-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
2010-01-14 14:37             ` sebastien dugue
2010-01-13 14:54 ` [PATCH 2/3] opensm/qos_policy: Add a new service ID and keyword for Lustre QoS sebastien dugue
2010-01-13 14:56 ` [PATCH 3/3] Add new port_space parameter to ko2iblnd module sebastien dugue

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=20100121092840.7429e81f@frecb007965 \
    --to=sebastien.dugue-6ktuutfb/bm@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=ogerlitz-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org \
    --cc=rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org \
    --cc=rolandd-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org \
    --cc=sashak-smomgflXvOZWk0Htik3J/w@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