[Cerowrt-devel] linksys ac1200 network bug

[Cerowrt-devel] linksys ac1200 network bug

[Dave Taht]

I went for a test drive of openwrt DESIGNATED DRIVER (Bleeding Edge,
r47665) today.

A) I bricked the archer c7 v2. No idea why.

B) I got a sorta working linksys 1200ac build.

The bad news: Any attempt to run 2 or more copies of netperf's
netserver on the 1200ac router with the default qdiscs (mq +
fq_codel), at line (gbit) rate, result in it locking up *for any other
traffic, including ping* until the first netperf is more or less
complete. I fear the underlying driver is  frightfully overbuffered,
or has another problem.

http://snapon.cs.kau.se/~d/archer-c7/onenetperflockout.png

(needs BQL, too)

The still bad news: cake works in both directions for a while longer,
then goes boom similarly.

The somewhat good news:

cake "shaped" to 900mbit on inbound and outbound to the router - does
not lock up the router. It merely runs out of cpu, but still does
manage quite respectable throughput in both  directions while doing
so. Note, I did not say "latency".

http://snapon.cs.kau.se/~d/archer-c7/encouraged.png

As usual there is some flent data in that dir if you want to draw your
own plots.

I was not in a position to actually test traffic through the router
(because I had the archer setup to do that)

I wouldn't draw any conclusions from this. Well, a safe conclusion,
is: don't install this build.

On Sat, Nov 28, 2015 at 11:41 AM, Dave Taht <dave.taht@gmail.com> wrote:
> Trying to do my first openwrt build in a while.
>
> make[5]: Leaving directory
> '/home/cero4/src/archer-c7/build_dir/target-mips_34kc_musl-1.1.11/dante-1.2.2'
> Makefile:349: recipe for target 'all' failed
>
> I checked: the package "dante" is not installed. Nor can I figure out
> what package is arbitrarily requiring it.
>
> I truly am in hell.

Simple patch for this, It involves invoking a deity.


> Dave Täht
> Let's go make home routers and wifi faster! With better software!
> https://www.gofundme.com/savewifi

Re: [Cerowrt-devel] linksys ac1200 network bug

[Dave Taht]

root@1200ac:~# uname -a
Linux 1200ac 3.18.23 #1 SMP Sat Nov 28 11:07:32 CET 2015 armv7l n

is my kernel. I see I can optionally build linux 4.0 for the linksys
1200ac at this point. Anyone doing that?
Dave Täht
Let's go make home routers and wifi faster! With better software!
https://www.gofundme.com/savewifi


On Sat, Nov 28, 2015 at 3:41 PM, Dave Taht <dave.taht@gmail.com> wrote:
> I went for a test drive of openwrt DESIGNATED DRIVER (Bleeding Edge,
> r47665) today.
>
> A) I bricked the archer c7 v2. No idea why.
>
> B) I got a sorta working linksys 1200ac build.
>
> The bad news: Any attempt to run 2 or more copies of netperf's
> netserver on the 1200ac router with the default qdiscs (mq +
> fq_codel), at line (gbit) rate, result in it locking up *for any other
> traffic, including ping* until the first netperf is more or less
> complete. I fear the underlying driver is  frightfully overbuffered,
> or has another problem.
>
> http://snapon.cs.kau.se/~d/archer-c7/onenetperflockout.png
>
> (needs BQL, too)
>
> The still bad news: cake works in both directions for a while longer,
> then goes boom similarly.
>
> The somewhat good news:
>
> cake "shaped" to 900mbit on inbound and outbound to the router - does
> not lock up the router. It merely runs out of cpu, but still does
> manage quite respectable throughput in both  directions while doing
> so. Note, I did not say "latency".
>
> http://snapon.cs.kau.se/~d/archer-c7/encouraged.png
>
> As usual there is some flent data in that dir if you want to draw your
> own plots.
>
> I was not in a position to actually test traffic through the router
> (because I had the archer setup to do that)
>
> I wouldn't draw any conclusions from this. Well, a safe conclusion,
> is: don't install this build.
>
> On Sat, Nov 28, 2015 at 11:41 AM, Dave Taht <dave.taht@gmail.com> wrote:
>> Trying to do my first openwrt build in a while.
>>
>> make[5]: Leaving directory
>> '/home/cero4/src/archer-c7/build_dir/target-mips_34kc_musl-1.1.11/dante-1.2.2'
>> Makefile:349: recipe for target 'all' failed
>>
>> I checked: the package "dante" is not installed. Nor can I figure out
>> what package is arbitrarily requiring it.
>>
>> I truly am in hell.
>
> Simple patch for this, It involves invoking a deity.
>
>
>> Dave Täht
>> Let's go make home routers and wifi faster! With better software!
>> https://www.gofundme.com/savewifi

Re: [Cerowrt-devel] linksys ac1200 network bug

[Dave Taht]

in the ac1750 front, this looked encouraging, but I haven't tried it -
https://mikepalmer.net/tp-link-archer-c7-ac1750-v2-tftp-recovery/

as for the linksys, my attempt to build 4.0 failed with it asking me
to completely regenerate my kernel config, which then didn't work. I
used to be able to make this work...

I was briefly happy thinking also that I could build for native float
format with

# CONFIG_SOFT_FLOAT is not set

as this arm is always hardware float and there seems to be no point in
not using the registers for it...

...and also enabling -O2 seemed like a good idea (as code generation
really seemed to suck with -Os for sch_cake)...

CONFIG_TARGET_OPTIMIZATION="-O2 -pipe -march=armv7-a -mtune=cortex-a9
-mfpu=vfpv3-d16"

But then I got:

/home/cero4/src/linksys_ac1200/staging_dir/toolchain-arm_cortex-a9+vfpv3_gcc-5.2.0_musl-1.1.11_eabi/include/linux/in6.h:49:8:
error: redefinition of 'struct sockaddr_in6'
 struct sockaddr_in6 {
        ^
In file included from
/home/cero4/src/linksys_ac1200/staging_dir/toolchain-arm_cortex-a9+vfpv3_gcc-5.2.0_musl-1.1.11_eabi/include/arpa/inet.h:9:0,
                 from
/home/cero4/src/linksys_ac1200/build_dir/target-arm_cortex-a9+vfpv3_musl-1.1.11_eabi/netifd-2015-11-17/system-linux.c:27:
/home/cero4/src/linksys_ac1200/staging_dir/toolchain-arm_cortex-a9+vfpv3_gcc-5.2.0_musl-1.1.11_eabi/include/netinet/in.h:36:8:
note: originally defined here
 struct sockaddr_in6
        ^
In file included from
/home/cero4/src/linksys_ac1200/staging_dir/toolchain-arm_cortex-a9+vfpv3_gcc-5.2.0_musl-1.1.11_eabi/include/linux/if_bridge.h:18:0,

Backing out each change, using my build box as a space heater...

Dave Täht
Let's go make home routers and wifi faster! With better software!
https://www.gofundme.com/savewifi


On Sat, Nov 28, 2015 at 3:45 PM, Dave Taht <dave.taht@gmail.com> wrote:
> root@1200ac:~# uname -a
> Linux 1200ac 3.18.23 #1 SMP Sat Nov 28 11:07:32 CET 2015 armv7l n
>
> is my kernel. I see I can optionally build linux 4.0 for the linksys
> 1200ac at this point. Anyone doing that?
> Dave Täht
> Let's go make home routers and wifi faster! With better software!
> https://www.gofundme.com/savewifi
>
>
> On Sat, Nov 28, 2015 at 3:41 PM, Dave Taht <dave.taht@gmail.com> wrote:
>> I went for a test drive of openwrt DESIGNATED DRIVER (Bleeding Edge,
>> r47665) today.
>>
>> A) I bricked the archer c7 v2. No idea why.
>>
>> B) I got a sorta working linksys 1200ac build.
>>
>> The bad news: Any attempt to run 2 or more copies of netperf's
>> netserver on the 1200ac router with the default qdiscs (mq +
>> fq_codel), at line (gbit) rate, result in it locking up *for any other
>> traffic, including ping* until the first netperf is more or less
>> complete. I fear the underlying driver is  frightfully overbuffered,
>> or has another problem.
>>
>> http://snapon.cs.kau.se/~d/archer-c7/onenetperflockout.png
>>
>> (needs BQL, too)
>>
>> The still bad news: cake works in both directions for a while longer,
>> then goes boom similarly.
>>
>> The somewhat good news:
>>
>> cake "shaped" to 900mbit on inbound and outbound to the router - does
>> not lock up the router. It merely runs out of cpu, but still does
>> manage quite respectable throughput in both  directions while doing
>> so. Note, I did not say "latency".
>>
>> http://snapon.cs.kau.se/~d/archer-c7/encouraged.png
>>
>> As usual there is some flent data in that dir if you want to draw your
>> own plots.
>>
>> I was not in a position to actually test traffic through the router
>> (because I had the archer setup to do that)
>>
>> I wouldn't draw any conclusions from this. Well, a safe conclusion,
>> is: don't install this build.
>>
>> On Sat, Nov 28, 2015 at 11:41 AM, Dave Taht <dave.taht@gmail.com> wrote:
>>> Trying to do my first openwrt build in a while.
>>>
>>> make[5]: Leaving directory
>>> '/home/cero4/src/archer-c7/build_dir/target-mips_34kc_musl-1.1.11/dante-1.2.2'
>>> Makefile:349: recipe for target 'all' failed
>>>
>>> I checked: the package "dante" is not installed. Nor can I figure out
>>> what package is arbitrarily requiring it.
>>>
>>> I truly am in hell.
>>
>> Simple patch for this, It involves invoking a deity.
>>
>>
>>> Dave Täht
>>> Let's go make home routers and wifi faster! With better software!
>>> https://www.gofundme.com/savewifi

Re: [Cerowrt-devel] linksys ac1200 network bug

[Dave Taht]

On Sat, Nov 28, 2015 at 10:19 PM, Imre Kaloz <kaloz@openwrt.org> wrote:
> Did you see https://lkml.org/lkml/2015/11/27/325 ? I'll try to find time to
> integrate a newer kernel and that patchset as well as
> https://lkml.org/lkml/2015/11/22/9 ,
> http://lkml.iu.edu/hypermail/linux/kernel/1511.0/04354.html and
> http://lists.openwall.net/netdev/2015/09/25/151

Nope, missed those. Thx!

At one level I hate it when I test something that is out of date, but
losing a day of testing to only being a day out of date, is
particularly annoying. :(

As I noted, I'm in love with those routing cache lookup fixes in
4.x.... I have a (bad) patch for BQL for this driver too that could
probably be fixed unless it landed already? (I am not sure how you do
xmit_more without BQL)

I will go back to testing on 4.1 on the archer for a while. The steps
to reproduce the bug I saw is merely try running two or more copies of
netperf to the router.

>
>
> Imre
>
>
> On Sat, 28 Nov 2015 15:41:17 +0100, Dave Taht <dave.taht@gmail.com> wrote:
>
>> I went for a test drive of openwrt DESIGNATED DRIVER (Bleeding Edge,
>> r47665) today.
>>
>> A) I bricked the archer c7 v2. No idea why.
>>
>> B) I got a sorta working linksys 1200ac build.
>>
>> The bad news: Any attempt to run 2 or more copies of netperf's
>> netserver on the 1200ac router with the default qdiscs (mq +
>> fq_codel), at line (gbit) rate, result in it locking up *for any other
>> traffic, including ping* until the first netperf is more or less
>> complete. I fear the underlying driver is  frightfully overbuffered,
>> or has another problem.
>>
>> http://snapon.cs.kau.se/~d/archer-c7/onenetperflockout.png
>>
>> (needs BQL, too)
>>
>> The still bad news: cake works in both directions for a while longer,
>> then goes boom similarly.
>>
>> The somewhat good news:
>>
>> cake "shaped" to 900mbit on inbound and outbound to the router - does
>> not lock up the router. It merely runs out of cpu, but still does
>> manage quite respectable throughput in both  directions while doing
>> so. Note, I did not say "latency".
>>
>> http://snapon.cs.kau.se/~d/archer-c7/encouraged.png
>>
>> As usual there is some flent data in that dir if you want to draw your
>> own plots.
>>
>> I was not in a position to actually test traffic through the router
>> (because I had the archer setup to do that)
>>
>> I wouldn't draw any conclusions from this. Well, a safe conclusion,
>> is: don't install this build.
>>
>> On Sat, Nov 28, 2015 at 11:41 AM, Dave Taht <dave.taht@gmail.com> wrote:
>>>
>>> Trying to do my first openwrt build in a while.
>>>
>>> make[5]: Leaving directory
>>>
>>> '/home/cero4/src/archer-c7/build_dir/target-mips_34kc_musl-1.1.11/dante-1.2.2'
>>> Makefile:349: recipe for target 'all' failed
>>>
>>> I checked: the package "dante" is not installed. Nor can I figure out
>>> what package is arbitrarily requiring it.
>>>
>>> I truly am in hell.
>>
>>
>> Simple patch for this, It involves invoking a deity.
>>
>>
>>> Dave Täht
>>> Let's go make home routers and wifi faster! With better software!
>>> https://www.gofundme.com/savewifi