From: "Sean Hefty" <sean.hefty@intel.com>
To: "'Jeff Garzik'" <jeff@garzik.org>,
"Steve Wise" <swise@opengridcomputing.com>
Cc: <netdev@vger.kernel.org>, <rdreier@cisco.com>,
<linux-kernel@vger.kernel.org>, <general@lists.openfabrics.org>,
"David Miller" <davem@davemloft.net>
Subject: RE: [ofa-general] Re: [PATCH RFC] RDMA/CMA: Allocate PS_TCP portsfrom the host TCP port space.
Date: Wed, 15 Aug 2007 20:27:26 -0700 [thread overview]
Message-ID: <000001c7dfb5$5e6ced20$4dc8180a@amr.corp.intel.com> (raw)
In-Reply-To: <46C3B5EF.5060409@garzik.org>
>It's not about being a niche. It's about creating a maintainable
>software net stack that has predictable behavior.
>
>Needing to reach out of the RDMA sandbox and reserve net stack resources
>away from itself travels a path we've consistently avoided.
We need to ensure that we're also creating a maintainable kernel. RDMA doesn't
use sockets, but that doesn't mean it's not part of the networking support
provided by the Linux kernel. Making blanket statements that RDMA should stay
within a sandbox is equivalent to saying that RDMA should duplicate any network
related functionality that it might need.
>>> I will NACK any patch that opens up sockets to eat up ports or
>>> anything stupid like that.
>
>Ditto for me as well.
I agree that using a socket is the wrong approach, but my guess is that it was
suggested as a possibility because of the attempt to keep RDMA in its 'sandbox'.
The iWarp architecture implements RDMA over TCP; it just doesn't use sockets.
The Linux network stack doesn't easily support this possibility. Are there any
reasonable ways to enable this to the degree necessary for iWarp?
- Sean
next prev parent reply other threads:[~2007-08-16 3:27 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-08-07 14:37 [PATCH RFC] RDMA/CMA: Allocate PS_TCP ports from " Steve Wise
2007-08-07 14:54 ` Evgeniy Polyakov
2007-08-07 15:06 ` Steve Wise
2007-08-07 15:39 ` Evgeniy Polyakov
2007-08-09 18:49 ` Steve Wise
2007-08-09 21:40 ` [ofa-general] " Sean Hefty
2007-08-09 21:55 ` David Miller
2007-08-09 23:22 ` Sean Hefty
2007-08-15 14:42 ` Steve Wise
2007-08-16 2:26 ` Jeff Garzik
2007-08-16 3:11 ` Roland Dreier
2007-08-16 3:27 ` Sean Hefty [this message]
2007-08-16 13:43 ` Tom Tucker
2007-08-16 21:17 ` David Miller
2007-08-17 19:52 ` Roland Dreier
2007-08-17 21:27 ` David Miller
2007-08-17 23:31 ` Roland Dreier
2007-08-18 0:00 ` David Miller
2007-08-18 5:23 ` Roland Dreier
2007-08-18 6:44 ` David Miller
2007-08-19 7:01 ` [ofa-general] Re: [PATCH RFC] RDMA/CMA: Allocate PS_TCP portsfrom " Sean Hefty
2007-08-19 7:23 ` David Miller
2007-08-19 17:33 ` [ofa-general] Re: [PATCH RFC] RDMA/CMA: Allocate PS_TCPportsfrom " Felix Marti
2007-08-19 19:32 ` David Miller
2007-08-19 19:49 ` Felix Marti
2007-08-19 23:04 ` David Miller
2007-08-20 0:32 ` Felix Marti
2007-08-20 0:40 ` David Miller
2007-08-20 0:47 ` Felix Marti
2007-08-20 1:05 ` David Miller
2007-08-20 1:41 ` Felix Marti
2007-08-20 11:07 ` Andi Kleen
2007-08-20 16:26 ` Felix Marti
2007-08-20 19:16 ` Rick Jones
2007-08-20 9:43 ` Evgeniy Polyakov
2007-08-20 16:53 ` Felix Marti
2007-08-20 18:10 ` Andi Kleen
2007-08-20 19:02 ` Felix Marti
2007-08-20 20:18 ` Thomas Graf
2007-08-20 20:33 ` Andi Kleen
2007-08-20 20:33 ` Patrick Geoffray
2007-08-21 4:21 ` Felix Marti
2007-08-19 23:27 ` Andi Kleen
2007-08-19 23:12 ` David Miller
2007-08-20 1:45 ` Felix Marti
2007-08-20 0:18 ` Herbert Xu
2007-08-21 1:16 ` [ofa-general] Re: [PATCH RFC] RDMA/CMA: Allocate PS_TCP ports from " Roland Dreier
2007-08-21 6:58 ` David Miller
2007-08-28 19:38 ` Roland Dreier
2007-08-28 20:43 ` David Miller
2007-10-08 21:54 ` Steve Wise
2007-10-09 13:44 ` James Lentini
2007-10-10 21:01 ` Sean Hefty
2007-10-10 23:04 ` David Miller
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='000001c7dfb5$5e6ced20$4dc8180a@amr.corp.intel.com' \
--to=sean.hefty@intel.com \
--cc=davem@davemloft.net \
--cc=general@lists.openfabrics.org \
--cc=jeff@garzik.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=rdreier@cisco.com \
--cc=swise@opengridcomputing.com \
/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
Powered by JetHome