netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: nikolay@cumulusnetworks.com
Cc: stephen@networkplumber.org, netdev@vger.kernel.org,
	roopa@cumulusnetworks.com, dsa@cumulusnetworks.com,
	jkbs@redhat.com, edumazet@google.com, pch@ordbogen.com
Subject: Re: [PATCH net-next v3] net: ipv4: add support for ECMP hash policy choice
Date: Tue, 14 Mar 2017 11:48:37 -0700 (PDT)	[thread overview]
Message-ID: <20170314.114837.619141079617104809.davem@davemloft.net> (raw)
In-Reply-To: <8088fe5f-0c0b-bdba-4fba-e9e28bbed02e@cumulusnetworks.com>

From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 14 Mar 2017 17:58:46 +0200

> On 14/03/17 17:55, Stephen Hemminger wrote:
>> On Tue, 14 Mar 2017 17:36:15 +0200
>> Nikolay Aleksandrov <nikolay@cumulusnetworks.com> wrote:
>> 
>>> This patch adds support for ECMP hash policy choice via a new sysctl
>>> called fib_multipath_hash_policy and also adds support for L4 hashes.
>>> The current values for fib_multipath_hash_policy are:
>>>  0 - layer 3 (default)
>>>  1 - layer 4
>>> If there's an skb hash already set and it matches the chosen policy then it
>>> will be used instead of being calculated (currently only for L4).
>>> In L3 mode we always calculate the hash due to the ICMP error special
>>> case, the flow dissector's field consistentification should handle the
>>> address order thus we can remove the address reversals.
>>>
>>> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
>> 
>> It is good to see ECMP come back from the grave.
>> Linux used to support it long ago but was abandoned after it was unstable
>> and removed from iproute2 in 2012.
>> 
>> The old API was through route attributes which makes more sense than
>> doing it with sysctl. It makes more sense to use netlink instead.
>> Therefore please go back and do something like the old API rather than doing it through
>> sysctl.
>> 
> 
> That's what my initial version did, but this was discussed during NetConf in Seville
> and it was decided that it's best to make a global sysctl, thus the change.

Correct, we discussed this, and we all agreed to only have a sysctl for now.

  reply	other threads:[~2017-03-14 18:48 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-06 14:59 [PATCH net-next] net: ipv4: add support for ECMP hash policy choice Nikolay Aleksandrov
2017-03-06 16:24 ` David Ahern
2017-03-06 16:52   ` Nikolay Aleksandrov
2017-03-07  6:16 ` Roopa Prabhu
2017-03-07 11:01 ` [PATCH net-next v2] " Nikolay Aleksandrov
2017-03-08 12:05   ` Jakub Sitnicki
2017-03-08 12:43     ` Nikolay Aleksandrov
2017-03-08 16:00       ` Jakub Sitnicki
2017-03-13  2:23         ` David Miller
2017-03-14 15:36   ` [PATCH net-next v3] " Nikolay Aleksandrov
2017-03-14 15:55     ` Stephen Hemminger
2017-03-14 15:58       ` Nikolay Aleksandrov
2017-03-14 18:48         ` David Miller [this message]
2017-03-14 20:25           ` Stephen Hemminger
2017-03-14 21:10             ` Roopa Prabhu
2017-03-14 21:42               ` Stephen Hemminger
2017-03-14 22:38                 ` Roopa Prabhu
2017-03-14 23:27                   ` Stephen Hemminger
2017-03-14 23:45                     ` David Ahern
2017-03-15  9:17                       ` Nicolas Dichtel
2017-03-15 10:46                         ` Nikolay Aleksandrov
2017-03-15 11:18                           ` Nicolas Dichtel
2017-03-15 11:27                             ` Nikolay Aleksandrov
2017-03-15 15:01                         ` David Ahern
2017-03-15 15:20                           ` Stephen Hemminger
2017-03-15  0:24             ` David Miller
2017-03-15  2:30               ` Tom Herbert
2017-03-17  3:36                 ` David Miller
2017-03-14 18:55     ` Nikolay Aleksandrov
2017-03-15 11:32     ` Jakub Sitnicki
2017-03-15 12:10       ` Nikolay Aleksandrov
2017-03-16 13:28   ` [PATCH net-next v4] " Nikolay Aleksandrov
2017-03-16 16:41     ` Stephen Hemminger
2017-03-16 16:49       ` Nikolay Aleksandrov
2017-03-17 10:06         ` Nikolay Aleksandrov
2017-03-21 22:28     ` 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=20170314.114837.619141079617104809.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=dsa@cumulusnetworks.com \
    --cc=edumazet@google.com \
    --cc=jkbs@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=nikolay@cumulusnetworks.com \
    --cc=pch@ordbogen.com \
    --cc=roopa@cumulusnetworks.com \
    --cc=stephen@networkplumber.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;
as well as URLs for NNTP newsgroup(s).