From: "Toke Høiland-Jørgensen" <toke@redhat.com>
To: Johannes Berg <johannes@sipsolutions.net>,
Herbert Xu <herbert@gondor.apana.org.au>
Cc: Arend Van Spriel <arend.vanspriel@broadcom.com>,
Felix Fietkau <nbd@nbd.name>,
linux-wireless@vger.kernel.org,
Eric Dumazet <eric.dumazet@gmail.com>,
netdev@vger.kernel.org
Subject: Re: [PATCH 5/5] mac80211: set NETIF_F_LLTX when using intermediate tx queues
Date: Tue, 16 Apr 2019 11:02:50 +0100 [thread overview]
Message-ID: <8736miuv1x.fsf@toke.dk> (raw)
In-Reply-To: <e4c1a3ca0c0c160b7c271ab83deebcf096f38497.camel@sipsolutions.net>
Johannes Berg <johannes@sipsolutions.net> writes:
> On Tue, 2019-04-16 at 17:37 +0800, Herbert Xu wrote:
>> On Tue, Apr 16, 2019 at 11:33:50AM +0200, Johannes Berg wrote:
>> > On Tue, 2019-04-16 at 10:33 +0100, Toke Høiland-Jørgensen wrote:
>> > >
>> > > > It is true because we have an entire buffering layer in mac80211 (in
>> > > > this case at least) and never push back to the stack.
>> > >
>> > > I'm wondering if we should be?
>> >
>> > I don't think so? We'd just buffer packets in yet another place.
>>
>> But you do realise that you're giving up on the rich queueing
>> functionality that Linux provides (net/sched),
>
> Yes, that was a trade-off we always knew about. The model that Linux
> provides is just not suited for wifi.
As explained at great length here:
https://www.usenix.org/conference/atc17/technical-sessions/presentation/hoilan-jorgesen
(you already know that of course, Johannes)
>> not to mention
>> breaking certain applications that rely on congestion feedback?
>
> This I don't understand. The congestion feedback happens through socket
> buffer space etc. which is still there (as long as nobody sneaks in an
> skb_orphan() call)
Sure, for TCP, the TSQ mechanism should keep the upper-level queue low
as long as the SKBs are alive. But is this also the case for UDP?
-Toke
next prev parent reply other threads:[~2019-04-16 10:02 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-16 17:06 [PATCH 1/5] mac80211: mesh: drop redundant rcu_read_lock/unlock calls Felix Fietkau
2019-03-16 17:06 ` [PATCH 2/5] mac80211: fix memory accounting with A-MSDU aggregation Felix Fietkau
2019-03-16 18:12 ` Toke Høiland-Jørgensen
2019-03-16 17:06 ` [PATCH 3/5] mac80211: calculate hash for fq without holding fq->lock in itxq enqueue Felix Fietkau
2019-03-16 18:13 ` Toke Høiland-Jørgensen
2019-03-16 17:06 ` [PATCH 4/5] mac80211: run late dequeue late tx handlers without holding fq->lock Felix Fietkau
2019-03-16 18:13 ` Toke Høiland-Jørgensen
2022-12-05 9:46 ` Wen Gong
2022-12-07 6:30 ` Wen Gong
2022-12-12 8:31 ` Wen Gong
2019-03-16 17:06 ` [PATCH 5/5] mac80211: set NETIF_F_LLTX when using intermediate tx queues Felix Fietkau
2019-03-16 18:14 ` Toke Høiland-Jørgensen
2019-04-14 9:44 ` Arend Van Spriel
2019-04-14 11:19 ` Felix Fietkau
2019-04-14 12:34 ` Arend Van Spriel
2019-04-16 7:34 ` Arend Van Spriel
2019-04-16 7:44 ` Herbert Xu
2019-04-16 8:04 ` Arend Van Spriel
2019-04-16 8:36 ` Herbert Xu
2019-04-16 8:37 ` Johannes Berg
2019-04-16 9:17 ` Arend Van Spriel
2019-04-16 9:29 ` Herbert Xu
2019-04-16 9:33 ` Toke Høiland-Jørgensen
2019-04-16 9:33 ` Johannes Berg
2019-04-16 9:37 ` Herbert Xu
2019-04-16 9:39 ` Johannes Berg
2019-04-16 10:02 ` Toke Høiland-Jørgensen [this message]
2019-04-17 2:11 ` Herbert Xu
2019-04-17 8:28 ` Toke Høiland-Jørgensen
2019-04-16 13:13 ` Herbert Xu
2019-04-16 13:18 ` Toke Høiland-Jørgensen
2019-04-17 3:38 ` Herbert Xu
2019-04-17 9:09 ` Toke Høiland-Jørgensen
2019-04-17 9:16 ` Arend Van Spriel
2019-04-17 9:17 ` Toke Høiland-Jørgensen
2019-04-23 12:41 ` Johannes Berg
2019-04-25 8:35 ` Herbert Xu
2019-04-25 8:39 ` Johannes Berg
2019-04-25 8:44 ` Herbert Xu
2019-04-25 8:49 ` Johannes Berg
2019-04-16 19:13 ` Johannes Berg
2019-04-17 2:13 ` Herbert Xu
2019-04-16 9:38 ` Toke Høiland-Jørgensen
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=8736miuv1x.fsf@toke.dk \
--to=toke@redhat.com \
--cc=arend.vanspriel@broadcom.com \
--cc=eric.dumazet@gmail.com \
--cc=herbert@gondor.apana.org.au \
--cc=johannes@sipsolutions.net \
--cc=linux-wireless@vger.kernel.org \
--cc=nbd@nbd.name \
--cc=netdev@vger.kernel.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).