From: John Fastabend <john.r.fastabend@intel.com>
To: David Miller <davem@davemloft.net>, roopa@cumulusnetworks.com
Cc: sfeldma@gmail.com, john.fastabend@gmail.com, jiri@resnulli.us,
netdev@vger.kernel.org
Subject: Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware
Date: Mon, 18 May 2015 17:21:29 -0700 [thread overview]
Message-ID: <555A8209.5000306@intel.com> (raw)
In-Reply-To: <20150518.161916.2132217836491222672.davem@davemloft.net>
On 05/18/2015 01:19 PM, David Miller wrote:
> From: Roopa Prabhu <roopa@cumulusnetworks.com>
> Date: Sun, 17 May 2015 16:42:05 -0700
>
>> On most systems where you can offload routes to hardware,
>> doing routing in software is not an option (the cpu limitations
>> make routing impossible in software).
>
> You absolutely do not get to determine this policy, none of us
> do.
>
> What matters is that by default the damn switch device being there
> is %100 transparent to the user.
>
> And the way to achieve that default is to do software routes as
> a fallback.
>
Although this is not really usable for a class of switches this way,
as noted above.
> I am not going to entertain changes of this nature which fail
> route loading by default just because we've exceeded a device's
> HW capacity to offload.
>
> I thought I was _really_ clear about this at netdev 0.1
So how about having an error strategy sysctl field that we can set
at provisioning time. I think this would align to Roopa's option (b).
This way we can default to "transparent" mode and the users where
this wont work can set the error mode. This way user land software
stacks that work today should continue to work in both modes.
.John
next prev parent reply other threads:[~2015-05-19 0:21 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-17 23:42 [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware Roopa Prabhu
2015-05-18 5:11 ` Scott Feldman
2015-05-18 20:19 ` David Miller
2015-05-19 0:21 ` John Fastabend [this message]
2015-05-19 3:48 ` David Miller
2015-05-19 5:58 ` roopa
2015-05-19 16:34 ` David Miller
2015-05-19 17:01 ` Jiri Pirko
2015-05-19 19:47 ` Andy Gospodarek
2015-05-19 20:28 ` David Miller
2015-05-20 14:37 ` Andy Gospodarek
2015-05-21 5:46 ` Scott Feldman
2015-05-21 15:37 ` roopa
2015-05-29 7:50 ` Jiri Pirko
2015-05-29 15:39 ` Scott Feldman
2015-05-30 9:00 ` Jiri Pirko
2015-05-31 4:19 ` John Fastabend
2015-05-31 6:34 ` Scott Feldman
2015-05-31 7:34 ` Scott Feldman
2015-05-19 5:57 ` roopa
2015-05-28 9:42 ` Jiri Pirko
2015-05-28 15:35 ` John Fastabend
2015-05-29 7:42 ` Jiri Pirko
2015-05-28 15:40 ` Scott Feldman
2015-05-28 16:10 ` John Fastabend
2015-05-29 5:37 ` roopa
2015-05-28 22:35 ` Andy Gospodarek
2015-05-29 5:51 ` roopa
2015-05-29 7:50 ` Jiri Pirko
2015-05-29 5:31 ` roopa
2015-05-29 15:12 ` Scott Feldman
2015-05-29 15:37 ` Jiri Pirko
-- strict thread matches above, loose matches on Subject: below --
2015-05-17 3:46 Roopa Prabhu
2015-05-17 23:41 ` roopa
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=555A8209.5000306@intel.com \
--to=john.r.fastabend@intel.com \
--cc=davem@davemloft.net \
--cc=jiri@resnulli.us \
--cc=john.fastabend@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=roopa@cumulusnetworks.com \
--cc=sfeldma@gmail.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;
as well as URLs for NNTP newsgroup(s).