From: Tobias Waldekranz <tobias@waldekranz•com>
To: Vladimir Oltean <olteanv@gmail•com>
Cc: Andrew Lunn <andrew@lunn•ch>, Marek Behun <marek.behun@nic•cz>,
vivien.didelot@gmail•com, f.fainelli@gmail•com,
netdev@vger•kernel.org
Subject: Re: [RFC PATCH 0/4] net: dsa: link aggregation support
Date: Tue, 27 Oct 2020 20:37:58 +0100 [thread overview]
Message-ID: <87blgnv4rt.fsf@waldekranz.com> (raw)
In-Reply-To: <20201027190034.utk3kkywc54zuxfn@skbuf>
On Tue, Oct 27, 2020 at 21:00, Vladimir Oltean <olteanv@gmail•com> wrote:
> On Tue, Oct 27, 2020 at 07:25:16PM +0100, Tobias Waldekranz wrote:
>> > 1) trunk user ports, with team/bonding controlling it
>> > 2) trunk DSA ports, i.e. the ports between switches in a D in DSA setup
>> > 3) trunk CPU ports.
> [...]
>> I think that (2) and (3) are essentially the same problem, i.e. creating
>> LAGs out of DSA links, be they switch-to-switch or switch-to-cpu
>> connections. I think you are correct that the CPU port can not be a
>> LAG/trunk, but I believe that limitation only applies to TO_CPU packets.
>
> Which would still be ok? They are called "slow protocol PDUs" for a reason.
Oh yes, completely agree. That was the point I was trying to make :)
>> In order for this to work on transmit, we need to add forward offloading
>> to the bridge so that we can, for example, send one FORWARD from the CPU
>> to send an ARP broadcast to swp1..4 instead of four FROM_CPUs.
>
> That surely sounds like an interesting (and tough to implement)
> optimization to increase the throughput, but why would it be _needed_
> for things to work? What's wrong with 4 FROM_CPU packets?
We have internal patches that do this, and I can confirm that it is
tough :) I really would like to figure out a way to solve this, that
would also be acceptable upstream. I have some ideas, it is on my TODO.
In a single-chip system I agree that it is not needed, the CPU can do
the load-balancing in software. But in order to have the hardware do
load-balancing on a switch-to-switch LAG, you need to send a FORWARD.
FROM_CPUs would just follow whatever is in the device mapping table. You
essentially have the inverse of the TO_CPU problem, but on Tx FROM_CPU
would make up 100% of traffic.
Other than that there are some things that, while strictly speaking
possible to do without FORWARDs, become much easier to deal with:
- Multicast routing. This is one case where performance _really_ suffers
from having to skb_clone() to each recipient.
- Bridging between virtual interfaces and DSA ports. Typical example is
an L2 VPN tunnel or one end of a veth pair. On FROM_CPUs, the switch
can not perform SA learning, which means that once you bridge traffic
from the VPN out to a DSA port, the return traffic will be classified
as unknown unicast by the switch and be flooded everywhere.
next prev parent reply other threads:[~2020-10-27 19:38 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-27 10:51 [RFC PATCH 0/4] net: dsa: link aggregation support Tobias Waldekranz
2020-10-27 10:51 ` [RFC PATCH 1/4] net: dsa: mv88e6xxx: use ethertyped dsa for 6390/6390X Tobias Waldekranz
2020-10-27 14:52 ` Marek Behun
2020-10-27 14:54 ` Marek Behun
2020-10-27 14:58 ` Marek Behun
2020-10-27 10:51 ` [RFC PATCH 2/4] net: dsa: link aggregation support Tobias Waldekranz
2020-10-28 0:58 ` Vladimir Oltean
2020-10-28 14:03 ` Tobias Waldekranz
2020-10-27 10:51 ` [RFC PATCH 3/4] net: dsa: mv88e6xxx: " Tobias Waldekranz
2020-10-27 10:51 ` [RFC PATCH 4/4] net: dsa: tag_edsa: support reception of packets from lag devices Tobias Waldekranz
2020-10-28 12:05 ` Vladimir Oltean
2020-10-28 15:28 ` Tobias Waldekranz
2020-10-28 18:18 ` Vladimir Oltean
2020-10-28 22:31 ` Tobias Waldekranz
2020-10-28 23:08 ` Vladimir Oltean
2020-10-29 7:47 ` Tobias Waldekranz
2020-10-30 9:21 ` Vladimir Oltean
2020-11-01 11:31 ` Ido Schimmel
2020-10-27 12:27 ` [RFC PATCH 0/4] net: dsa: link aggregation support Vladimir Oltean
2020-10-27 14:29 ` Andrew Lunn
2020-10-27 14:59 ` Tobias Waldekranz
2020-10-27 14:00 ` Andrew Lunn
2020-10-27 15:09 ` Tobias Waldekranz
2020-10-27 15:05 ` Marek Behun
2020-10-27 15:23 ` Andrew Lunn
2020-10-27 18:25 ` Tobias Waldekranz
2020-10-27 18:33 ` Marek Behun
2020-10-27 19:04 ` Vladimir Oltean
2020-10-27 19:21 ` Tobias Waldekranz
2020-10-27 19:00 ` Vladimir Oltean
2020-10-27 19:37 ` Tobias Waldekranz [this message]
2020-10-27 20:02 ` Vladimir Oltean
2020-10-27 20:53 ` Tobias Waldekranz
2020-10-27 22:32 ` Vladimir Oltean
2020-10-28 0:27 ` Tobias Waldekranz
2020-10-28 22:35 ` Marek Behun
2020-10-27 22:36 ` Andrew Lunn
2020-10-28 0:45 ` Tobias Waldekranz
2020-10-28 1:03 ` Andrew Lunn
2020-11-11 4:28 ` Florian Fainelli
2020-11-19 10:51 ` Vladimir Oltean
2020-11-19 11:52 ` Tobias Waldekranz
2020-11-19 18:12 ` Vladimir Oltean
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=87blgnv4rt.fsf@waldekranz.com \
--to=tobias@waldekranz$(echo .)com \
--cc=andrew@lunn$(echo .)ch \
--cc=f.fainelli@gmail$(echo .)com \
--cc=marek.behun@nic$(echo .)cz \
--cc=netdev@vger$(echo .)kernel.org \
--cc=olteanv@gmail$(echo .)com \
--cc=vivien.didelot@gmail$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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