From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qg0-x231.google.com (mail-qg0-x231.google.com [IPv6:2607:f8b0:400d:c04::231]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 219FA21F428; Thu, 19 Feb 2015 21:33:00 -0800 (PST) Received: by mail-qg0-f49.google.com with SMTP id q107so12055046qgd.8; Thu, 19 Feb 2015 21:32:59 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=tK4NKwyUEw4IF8YB55i1rB3XXXtG8DB8+rpW0vDATFE=; b=pB6z3NDaJFAbyP3FmIwzntE6uEtbNEx+HGRQANDM1tfP6JUQ/sOhM80pjauHIt5a1t p6lR3cJ6ny+NI/TVgzMP27pTGjdVy8x9UiT6fJjsioqQAaCiZpr8cXNlFljBoznud25U UR4hUPHvFaLBwGNukmNFNSROpPBdyEIJ2n6BTD+UgWS4wsNQw/E0xML9EmgoW/r97Gvc IMt4h/i8DNmwyuuXnZJ16Nb26ZVhy7uHZGoPPtDhNpwPkBRUa9cAF1FOXPsR64kuloL7 OfmUCIzsgY/5/gsm2E+97njQQPbRsoPfrmpDk1IcATsdLtVtVS9oLzky0JnMEGYJdj5I WeSw== MIME-Version: 1.0 X-Received: by 10.229.175.131 with SMTP id ba3mr3966213qcb.3.1424410379469; Thu, 19 Feb 2015 21:32:59 -0800 (PST) Received: by 10.96.231.35 with HTTP; Thu, 19 Feb 2015 21:32:59 -0800 (PST) In-Reply-To: References: Date: Thu, 19 Feb 2015 21:32:59 -0800 Message-ID: From: Aaron Wood To: Dave Taht Content-Type: multipart/alternative; boundary=001a11c2875aaecab0050f7e626d Cc: cerowrt-devel , bloat Subject: Re: [Cerowrt-devel] [Bloat] Two d-link products tested for bloat... X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 20 Feb 2015 05:33:29 -0000 --001a11c2875aaecab0050f7e626d Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Perhaps just a wall of shame? No venom, just point out the failings, and call people out. But, frankly, I don't think any of the router mfr's actually care (I've seen no evidence of it), and since they're not in the business of actually making these things (just putting their labels on them), I don't see them being able to drive it in a coherent manner. I'm appalled that the silicon vendors aren't in on this. Because frankly _this_ is the sort of thing that they can use to distinguish themselves. But as usual, they seem more interested in butchering the open source software to make something "proprietary", which is full of bugs and poor performance except in a narrow lab setup. The people that I expect to do better at this are the Ubiquiti and others, which _are_ doing hardware design (to some degree), and building the software that goes on top of it as well. -Aaron On Thu, Feb 19, 2015 at 6:04 PM, Dave Taht wrote: > I ordered a d-link DGL-5500 from amazon this week. It arrived today. > This is their almost top of the line 802.11ac router. > > Their streamboost QoS feature - the first thing you see on their > configuration page - LOVELY gui, actually! - was entirely broken in > the uplink direction. > > Admittedly that was the first generation firmware. I know how hard it > is to get that right. So I tried to update it. My attempt to update > the firmware for it from their website, bricked it. And it appears the > only way to update it, or to update it to openwrt, is via a gui, not > tftp. > > ok.... so... > > In an orgy of giving companies that don=C2=B4t deserve my money, money, > I also got the DIR-860L. It was the "A1" model, which of course, has > no support in openwrt, and there is no way to figure out if an online > retailer is selling the entirely different B model or not. > > Their version of the QoS system was entirely broken in *both > directions*. While I was mildly happy that it used weighted fair > queuing by default, bandwidth limitation failed to work *at all*, > except, that it did classify CS1 traffic, as *higher* priority than > best effort. > > So in both cases, no matter what you did, even if you tried to do the > right thing... you had bufferbloat induced on the next hop (if, I was > trying to actually test this on a cablemodem or dsl link) > > I would really to flush this crap from the marketplace, and the only > way left, I think, is to stop being a nice guy. > > My problem is, that I really am a nice guy, and the only way I could > possibly do that is put on a persona, do a blog, call it something > like the angry engineer, or something like that. > > But I am pretty sure that venom I would have to summon on a daily > basis would be bad for my blood pressure. Maybe we could all get > together on it, and only raise our collective BP by a point or three > each? The Avenging Engineers? > > the relevant netperf-wrapper data is in each of these dirs: > > > http://snapon.lab.bufferbloat.net/~d/DIR-860L/dir-860L-bandwidth-broke-in= -both-directions.png > > > http://snapon.lab.bufferbloat.net/~d/dgl-5500/totalfailure-to-control-the= -upload.png > > On Wed, Feb 18, 2015 at 1:28 AM, Sebastian Moeller > wrote: > > Hi Felix, hi List, > > > > > > On Jan 25, 2015, at 12:09 , Felix Fietkau wrote: > > > >> Here's another candidate: > >> > http://us.dlink.com/products/connect/wireless-ac1200-dual-band-gigabit-cl= oud-router-dir-860l/ > >> > >> CPU: MT7621 (dual-core MIPS, 880 MHz, 4 virtual CPUs) > >> The device has preliminary OpenWrt support already. In my tests, handl= es > >> ~820 Mbit/s NAT without any special acceleration features (with > fq_codel, > >> no shaping). Haven't done any tests with shaping yet. > >> Wifi (MT7612E) is still buggy with my mt76 driver, but I'll fix that i= n > >> March when I get back from vacation. > >> > >> - Felix > > > > I am currently searching for a replacement for my wndr3700v2 as > it is running out of steam on my temporary 100/40 Mbps link. This thing > looks quite decent, but I notice between > https://wikidevi.com/wiki/D-Link_DIR-860L_rev_A1 and > https://wikidevi.com/wiki/D-Link_DIR-860L_rev_B1 that d-link reused the > sam name for quite different hardware implementations, and only the more > recent B1 revision will work for us. (Is it just me or do you also find > this tendency to not even add the revision to the official name a bit > annoying?) > > So, does anybody here now how to order a specific revision in > Germany? Or is the only way to wait a bit and hope the A1 revision clears > the retail channel so only B1=E2=80=99s are left? I notice that from look= ing at the > internal photos for both devices posted on the FCC site that the old A1 > Broadcom revision has its USB port "above" the ethernet ports while the B= 1 > Mediatek revision has the USB port between DC in and below the ethernet > ports. Am I correct in assuming that deployed hardware needs to match the > FCC design exactly (that is, in case of revision a new FCC submission wit= h > new photos is required)? > > > > Best Regards > > Sebastian > > > > -- > Dave T=C3=A4ht > > thttp://www.bufferbloat.net/projects/bloat/wiki/Upcoming_Talks > _______________________________________________ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat > --001a11c2875aaecab0050f7e626d Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable
Perhaps just a wall of shame?=C2=A0 No venom, just point o= ut the failings, and call people out.

But, frankly, I do= n't think any of the router mfr's actually care (I've seen no e= vidence of it), and since they're not in the business of actually makin= g these things (just putting their labels on them), I don't see them be= ing able to drive it in a coherent manner.=C2=A0 I'm appalled that the = silicon vendors aren't in on this.=C2=A0 Because frankly _this_ is the = sort of thing that they can use to distinguish themselves.=C2=A0 But as usu= al, they seem more interested in butchering the open source software to mak= e something "proprietary", which is full of bugs and poor perform= ance except in a narrow lab setup.

The people that= I expect to do better at this are the Ubiquiti and others, which _are_ doi= ng hardware design (to some degree), and building the software that goes on= top of it as well.

-Aaron

On Thu, Feb 19, 2015 at 6:0= 4 PM, Dave Taht <dave.taht@gmail.com> wrote:
I ordered a d-link DGL-5500 from amazon this week. It = arrived today.
This is their almost top of the line 802.11ac router.

Their streamboost QoS feature - the first thing you see on their
configuration page - LOVELY gui, actually! - was entirely broken in
the uplink direction.

Admittedly that was the first generation firmware. I know how hard it
is to get that right. So I tried to update it. My attempt to update
the firmware for it from their website, bricked it. And it appears the
only way to update it, or to update it to openwrt, is via a gui, not
tftp.

ok.... so...

In an orgy of giving companies that don=C2=B4t deserve my money, money,
I also got the DIR-860L. It was the "A1" model, which of course, = has
no support in openwrt, and there is no way to figure out if an online
retailer is selling the entirely different B model or not.

Their version of the QoS system was entirely broken in *both
directions*. While I was mildly happy that it used weighted fair
queuing by default, bandwidth limitation failed to work *at all*,
except, that it did classify CS1 traffic, as *higher* priority than
best effort.

So in both cases, no matter what you did, even if you tried to do the
right thing... you had bufferbloat induced on the next hop (if, I was
trying to actually test this on a cablemodem or dsl link)

I would really to flush this crap from the marketplace, and the only
way left, I think, is to stop being a nice guy.

My problem is, that I really am a nice guy, and the only way I could
possibly do that is put on a persona, do a blog, call it something
like the angry engineer, or something like that.

But I am pretty sure that venom I would have to summon on a daily
basis would be bad for my blood pressure. Maybe we could all get
together on it, and only raise our collective BP by a point or three
each? The Avenging Engineers?

the relevant netperf-wrapper data is in each of these dirs:

http://snapon.lab.bufferbl= oat.net/~d/DIR-860L/dir-860L-bandwidth-broke-in-both-directions.png

http://snapon.lab.bufferbloat.net/~= d/dgl-5500/totalfailure-to-control-the-upload.png

On Wed, Feb 18, 2015 at 1:28 AM, Sebastian Moeller <moeller0@gmx.de> wrote:
> Hi Felix, hi List,
>
>
> On Jan 25, 2015, at 12:09 , Felix Fietkau <nbd@openwrt.org> wrote:
>
>> Here's another candidate:
>> http://us.dlink.c= om/products/connect/wireless-ac1200-dual-band-gigabit-cloud-router-dir-860l= /
>>
>> CPU: MT7621 (dual-core MIPS, 880 MHz, 4 virtual CPUs)
>> The device has preliminary OpenWrt support already. In my tests, h= andles
>> ~820 Mbit/s NAT without any special acceleration features (with fq= _codel,
>> no shaping). Haven't done any tests with shaping yet.
>> Wifi (MT7612E) is still buggy with my mt76 driver, but I'll fi= x that in
>> March when I get back from vacation.
>>
>> - Felix
>
>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0I am currently searching for a replac= ement for my wndr3700v2 as it is running out of steam on my temporary 100/4= 0 Mbps link. This thing looks quite decent, but I notice between https:= //wikidevi.com/wiki/D-Link_DIR-860L_rev_A1 and https://wikidevi.com= /wiki/D-Link_DIR-860L_rev_B1 that d-link reused the sam name for quite = different hardware implementations, and only the more recent B1 revision wi= ll work for us. (Is it just me or do you also find this tendency to not eve= n add the revision to the official name a bit annoying?)
>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0So, does anybody here now how to orde= r a specific revision in Germany? Or is the only way to wait a bit and hope= the A1 revision clears the retail channel so only B1=E2=80=99s are left? I= notice that from looking at the internal photos for both devices posted on= the FCC site that the old A1 Broadcom revision has its USB port "abov= e" the ethernet ports while the B1 Mediatek revision has the USB port = between DC in and below the ethernet ports. Am I correct in assuming that d= eployed hardware needs to match the FCC design exactly (that is, in case of= revision a new FCC submission with new photos is required)?
>
> Best Regards
>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0Sebastian



--
Dave T=C3=A4ht

thttp://www.bufferbloat.net/projects/bloat/wiki/Upcoming_T= alks
_______________________________________________
Bloat mailing list
Bloat@lists.bufferbloat.net<= /a>
= https://lists.bufferbloat.net/listinfo/bloat

--001a11c2875aaecab0050f7e626d--