Received-SPF: pass (google.com: domain of linux-wireless+bounces-4487-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Message-ID: <29f7aa2c233277ab4bb56bcff8e228036ee96a2e.camel@sipsolutions.net>
Subject: Re: regression: [PATCH] wifi: mac80211: set station RX-NSS on
 reconfig
From: Johannes Berg <johannes@sipsolutions.net>
To: Andreas Tobler <andreas.tobler@onway.ch>, linux-wireless@vger.kernel.org
Date: Fri, 08 Mar 2024 13:19:54 +0100
In-Reply-To: <014a25e4-5609-4e3e-a593-8a2bf1bd5568@onway.ch>
References: <014a25e4-5609-4e3e-a593-8a2bf1bd5568@onway.ch>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
User-Agent: Evolution 3.50.4 (3.50.4-1.fc39) 
Precedence: bulk
MIME-Version: 1.0

On Fri, 2024-03-08 at 12:58 +0100, Andreas Tobler wrote:
> Hello Johannes, all.
>=20
> with this commit[0] we encounter a performance regression in one of our=
=20
> AP/STA tests. The performance drop is about 100Mbps+
>=20
> Our setup is a hostap (2.10) configured AP on 802.11ac, channel 46.=20
> (40MHz). The client connects via wpa (2.10) and then we produce traffic.=
=20
> Before this commit, the throughput was around 250 Mbps, with this commit=
=20
> the performance is now down to 135 Mbps.
>=20
> The wifi cards we use are WLE600VX from compex, a ath10k based one. The=
=20
> kernel we're on is 6.1.80. We've seen it on 6.6 too but didn't investigat=
e.
>=20
> Now, the ieee80211_sta_set_rx_nss() function has two FIXME comments. One=
=20
> in where it handles the ht capability and one in the vht part. Both=20
> FIXME's are: 'consider rx_highest?'
>=20

I think you'll find that all that is unrelated, and this fixes it:

https://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git/=
commit/?id=3Da8bca3e9371dc5e276af4168be099b2a05554c2a

johannes