Message-ID: <1424775580.2192.31.camel@sipsolutions.net> (sfid-20150224_115958_819461_2AD97E2A)
Subject: Re: Throughput regression with `tcp: refine TSO autosizing`
From: Johannes Berg <johannes@sipsolutions.net>
To: Michal Kazior <michal.kazior@tieto.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
	Neal Cardwell <ncardwell@google.com>,
	linux-wireless <linux-wireless@vger.kernel.org>,
	Network Development <netdev@vger.kernel.org>,
	Eyal Perry <eyalpe@dev.mellanox.co.il>
Date: Tue, 24 Feb 2015 11:59:40 +0100
In-Reply-To: <1424773829.2192.26.camel@sipsolutions.net> (sfid-20150224_113053_601266_2B6FD03E)
References: <CA+BoTQkVu23P3EOmY_Q3E1GJnWsyF==Pawz4iPOS_Bq5dvfO5Q@mail.gmail.com>
	 <1422537297.21689.15.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQk2xT-8DqPuiiKG+kHAjLPrj8F9dLTb-rcGhvMq0u_2Qw@mail.gmail.com>
	 <1422628835.21689.95.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQkV+mOZfe_Niz5101sMQeaV6muKCsShptjGQ1AgOHqqoQ@mail.gmail.com>
	 <1422903136.21689.114.camel@edumazet-glaptop2.roam.corp.google.com>
	 <1422926330.21689.138.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQkMikA8wxm1ce2DkKhPB0HiKeAqT7f+sQ=91W40z=X0Rg@mail.gmail.com>
	 <1422973660.907.10.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQmvUuFdfYF=wVMYxrf_nQZB5GCV=LvDZVvfs-3hAE4WKw@mail.gmail.com>
	 <1423051045.907.108.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQ=BDcQ779uKCuX+f40=4npXVF4MTQnpjKimNYAxPsxBoQ@mail.gmail.com>
	 <1423053531.907.115.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQ=qmCZz4CmSOvCOzMLowrDEG12XBffkTcYxjGqVD9604g@mail.gmail.com>
	 <1423055810.907.125.camel@edumazet-glaptop2.roam.corp.google.com>
	 <1423056591.907.130.camel@edumazet-glaptop2.roam.corp.google.com>
	 <1423084303.31870.15.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQnnwrv0nrKyGyQNvosz_E4e5fBa9iN8fpeqcd-iRfi17g@mail.gmail.com>
	 <1423141038.31870.38.camel@edumazet-glaptop2.roam.corp.google.com>
	 <1423142342.31870.49.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQmcShK0U_cXvEOLY_8y7LH8x3taTgjcyMzv0MLVn4UtCA@mail.gmail.com>
	 <1423147286.31870.59.camel@edumazet-glaptop2.roam.corp.google.com>
	 <1423156205.31870.86.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQ=WaKLV=r6qWaWAEfyDr2pqMWpm4NDmnek92TEVndnxRQ@mail.gmail.com>
	 <1423230001.31870.128.camel@edumazet-glaptop2.roam.corp.google.com>
	 <1423230785.31870.131.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQkazCOin7VWLfrHUjtgKDPV6T+sFsk5FPS7D-morr4FZQ@mail.gmail.com>
	 <CA+BoTQn3KRym0qCJ+fLav5LQgjfiN_-Eqz0xPSc2eXJ-ijNjQw@mail.gmail.com>
	 <1423494690.31870.189.camel@edumazet-glaptop2.roam.corp.google.com>
	 <CA+BoTQ=u_xPuqTVOVaFTQNRrJ+UTXe89SY+=+7Y1LpxxrkRDfg@mail.gmail.com>
	 <1423577962.2215.2.camel@sipsolutions.net>
	 <CA+BoTQn=YQQ_yUHvpAG3MMAw+=jxgLDiUMWxiTC3B3vkksTw9g@mail.gmail.com>
	 <CA+BoTQnxo-x94uVfErZO43jTowVcEMEt+7xDzoAGiR8fRDv=ug@mail.gmail.com>
	 (sfid-20150212_084824_976893_36D95ADD) <1424773495.2192.23.camel@sipsolutions.net>
	 (sfid-20150224_112513_283616_0F65D43B) <1424773829.2192.26.camel@sipsolutions.net>
	 (sfid-20150224_113053_601266_2B6FD03E)
Content-Type: text/plain; charset="UTF-8"
Mime-Version: 1.0
Sender: linux-wireless-owner@vger.kernel.org

On Tue, 2015-02-24 at 11:30 +0100, Johannes Berg wrote:
> On Tue, 2015-02-24 at 11:24 +0100, Johannes Berg wrote:
> > On Thu, 2015-02-12 at 08:48 +0100, Michal Kazior wrote:
> > 
> > > > Good point. I was actually thinking about it. I can try cooking a
> > > > patch unless you want to do it yourself :-)
> > > 
> > > I've taken a look into this. The most obvious place to add the
> > > timestamp for each packet would be ieee80211_tx_info (i.e. the
> > > skb->cb[48]). The problem is it's very tight there. Even squeezing 2
> > > bytes (allowing up to 64ms of tx completion delay which I'm worried
> > > won't be enough) will be troublesome. Some drivers already use every
> > > last byte of their allowance on 64bit archs (e.g. ar5523 uses entire
> > > 40 bytes of driver_data).
> > 
> > Couldn't we just repurpose the existing skb->tstamp field for this, as
> > long as the skb is fully contained within the wireless layer?
> > 
> > Actually, it looks like we can't, since I guess timestamping options can
> > be turned on on any socket.
> 
> Actually, that creates a clone or a new skb? Hmm.

Ah and then it puts it on the error queue right away, so I think we can
reuse it.

johannes