From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-oi0-x232.google.com (mail-oi0-x232.google.com [IPv6:2607:f8b0:4003:c06::232]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 072543B29E for ; Sun, 26 Aug 2018 21:54:02 -0400 (EDT) Received: by mail-oi0-x232.google.com with SMTP id y207-v6so24552435oie.13 for ; Sun, 26 Aug 2018 18:54:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc:content-transfer-encoding; bh=jd+Q9T4sBxLWDAj4ND0zh7UvNtzI070Ts3sbrxnALUU=; b=Pt3ikGJypBNCdJqzdoQjhjNl8CadJpVcRkhywae6NMqSwGdDhJPIunnZUDuruLIXDp LUjUBMBBB5wMe6S8bEEQ3tm0OlGBdiPs5TKus0vySfxI+44JP3ZNOL6tYfPIiOSH8Aez flYtfLKtD0/WoSm7I1B+hArVvLmd5/OBdlqyAa5wkhMaqo8/1lbDZ4WnUlRj8Df5XO6c mZ6nEl70tcU1zSzK1TKgEoR4ilj/MFHsEOyzqQkYKiBFl89HXSak4ON8jAiNxQuMYRkn nknmtVbaUy62R9gjrcgLvMVs7jP6doT9DcKPOuCJlUGY/gKQUUuG18my4LwKoZTeqHcE 9ymQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc:content-transfer-encoding; bh=jd+Q9T4sBxLWDAj4ND0zh7UvNtzI070Ts3sbrxnALUU=; b=d8dZmpMvPbdX2PocncCMoOiVfNl90sru3ADUWWBTPY/NM/vl5++dFwxtNf77WmK9oa /XJjIfzzj5Sv7OYyKcmwY+JU/wL4713EerTeSyCYU1jB413XZQBi0eFZk0Mxu1sN+PPQ TBj2yChFoY5DJezSLB7tq4Bibg6Z86wcsPaxZlT/Ud4/CCyXbNGTr3o1jv95QVOgJZAL aF5QoevIaeUw+zayFvvGk1zeFskCmphYVVoERp02vYSLNI12rRGd7mOvsqSqD0GDUo0J VZJs2BoW3qAlecXLENXtmH2FqsR3irGWdrQcy3Nd6eudITAsxcELpgY94JBewX+DYJBu 8wAA== X-Gm-Message-State: APzg51DSY2PbOd0Rx4Zs9HsY1HbqeWIvkNNxaj77+TfRSo2shRniUi9L iBRzrVvvKdUd5yPO43UP5R+za0hAS0ncl964K2o= X-Google-Smtp-Source: ANB0VdYq6+KKmCKD4vxAs5cv7ydw+8LrJnzrTSzvQ46zmNN36P2FuGQoXRgv9aFnuKZKLqZyp1ZYeKDMnujDG2YMLbo= X-Received: by 2002:aca:bc54:: with SMTP id m81-v6mr11131582oif.308.1535334842292; Sun, 26 Aug 2018 18:54:02 -0700 (PDT) MIME-Version: 1.0 References: <66e2374b-f998-b132-410e-46c9089bb06b@gmail.com> <360212B1-8411-4ED0-877A-92E59070F518@gmx.de> In-Reply-To: From: Rosen Penev Date: Sun, 26 Aug 2018 18:53:54 -0700 Message-ID: To: Dave Taht Cc: Mikael Abrahamsson , bloat Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Subject: Re: [Bloat] Marvell 385 X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 27 Aug 2018 01:54:03 -0000 On Sun, Aug 26, 2018 at 6:45 PM Dave Taht wrote: > > On Sun, Aug 26, 2018 at 6:33 PM Rosen Penev wrote: > > > > On Sun, Aug 26, 2018 at 6:20 PM Dave Taht wrote: > > > > > > On Sun, Aug 26, 2018 at 5:55 PM Rosen Penev wrote: > > > > > > > > On Sun, Aug 26, 2018 at 2:09 PM Dave Taht wro= te: > > > > > > > > > > On Sun, Aug 26, 2018 at 1:58 PM Rosen Penev wr= ote: > > > > > > > > > > > > On Sun, Aug 26, 2018 at 11:44 AM Mikael Abrahamsson wrote: > > > > > > > > > > > > > > On Sat, 25 Aug 2018, Dave Taht wrote: > > > > > > > > > > > > > > > The expressobin is a Marvell Armada "3700LP (88F3720) dual = core ARM > > > > > > > > Cortex A53 processor up to 1.2GHz" - how does that compare?= I have > > > > > > > > plenty of ath10k and ath9k pcmcia cards.... > > > > > > > > > > > > > > I have one of these, incl wifi. Right now the drivers are not= in great > > > > > > > shape, but they're being worked on. My espressobin has worse = performance > > > > > > > than on its wired ports than my WRT1200AC (Armada 385). > > > > > > If as you mentioned earlier that ethernet performance is limite= d by > > > > > > interrupts, then this commit is kind of depressing: > > > > > > > > > > > > https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next= .git/commit/drivers/net/ethernet/marvell/mvneta.c?h=3Dnext-20180824&id=3D0f= 5c6c30a0f8c629b92ecdaef61b315c43fde10a > > > > > > > > > > I was on that thread. It was broken before entirely. As for the s= ingle > > > > > interrupt on this chip variant - believe it or not, I'm not huge = on > > > > > lots of different interrupts for everything. I'd like it if we ha= d > > > > > more than an rx or tx interrupt > > > > > in general, I'd love it if we had a programmable "tx is almost do= ne" > > > > > interrupt that you could tune to the > > > > > interrupt latency... and it's complicated and costs wires to have= lots > > > > > of different interrupt types... and (fantasizing again) I'd love = it if > > > > > we had a scratchpad or dedicated memory to store interrupt handle= rs in > > > > > rather than relying on cache.... > > > > > > > > > > I'd looked deeply into improving this driver once upon a time, an= d > > > > > wanted to rip the software gro out of it, > > > > > in particular, and not defer things as much, trying things like N= API > > > > > of 16 and measuring where time was spent. The copy to memory is > > > > > expensive, and then it defers further work. > > > > > > > > > > Less code, particularly near interrupt time, is better than a lot= . > > > > > adding XMIT_MORE to the ar71xx driver (which hurt it badly) is on= e > > > > > example. > > > > I've been looking a lot at ag71xx. The driver has so much low hangi= ng > > > > fruit. Unfortunately I lack the knowledge to fix most of it. > > > > > > > > This patch for example gives me a ~20-30mbps improvement in iperf > > > > tests: https://pastebin.com/ZExWjXQZ > > > > > > cool! that driver as widely used as it is has never had enough eyebal= ls on it. > > No. Definitely not enough. > > > > > > Have you put that patch in front of the openwrt folk? I note that tha= t > > > driver didn't > > > used to live in that part of the tree - have they finally moved over? > > Yeah I did. Felix rejected it on the grounds that he didn't understand > > it. So I've just been keeping it in my tree. The patch itself comes > > from an old SDK by Qualcomm. > > Hmm. By eyeball I can't see how it could speed up things that much either= . :) Me and another user's thinking is that it causes fewer cache misses. I ported one of Felix' patches that he did for ramips where he got rid of netdev_alloc_frag and was disappointed to find out that performance dropped by 40mbps. That was fixed just by moving the new struct member higher. So yeah. Lots of low hanging fruit. > > But I used to be willig to bnchmark. not thi month though No worries. > > > > > > > > > > > > > > > > > It's kind of unfortunate given how much atheros hardware is out the= re. > > > > > > > > > > Given something *cool* now landing ( skb list batching, see lwn )= it > > > > > would be worthwhile to revisit this. I don't care if I get more > > > > > interrupts/sec (particularly on a multicore) if we could drain th= e rx > > > > > ring over smaller intervals... > > > > > > > > > > but that's me, I'm all about the latency. :) Nobody's willing to = rip > > > > > the latency out of stuff, they'd rather add features. It's really= hard > > > > > to correctly measure interrupt latency regardless. > > > > > > > > > > > > > > > > > > > > > > > > I have talked to people who say the drivers are being worked = on though... > > > > > > > If you have input, Kaloz is probably a great person to take t= hat input. I > > > > > > > know other people working on Marvell drivers as well. > > > > > > > > > > > > > > -- > > > > > > > Mikael Abrahamsson email: swmike@swm.pp.se > > > > > > > _______________________________________________ > > > > > > > Bloat mailing list > > > > > > > Bloat@lists.bufferbloat.net > > > > > > > https://lists.bufferbloat.net/listinfo/bloat > > > > > > > > > > > > > > > > > > > > -- > > > > > > > > > > Dave T=C3=A4ht > > > > > CEO, TekLibre, LLC > > > > > http://www.teklibre.com > > > > > Tel: 1-669-226-2619 > > > > > > > > > > > > -- > > > > > > Dave T=C3=A4ht > > > CEO, TekLibre, LLC > > > http://www.teklibre.com > > > Tel: 1-669-226-2619 > > > > -- > > Dave T=C3=A4ht > CEO, TekLibre, LLC > http://www.teklibre.com > Tel: 1-669-226-2619