From: Sebastian Moeller <moeller0@gmx.de>
To: Mikael Abrahamsson <swmike@swm.pp.se>
Cc: cerowrt-devel <cerowrt-devel@lists.bufferbloat.net>
Subject: Re: [Cerowrt-devel] performance numbers from WRT1200AC (Re: Latest build test - new sqm-scripts seem to work; "cake overhead 40" didn't)
Date: Fri, 26 Jun 2015 11:46:19 +0200 [thread overview]
Message-ID: <43D5C3CE-F1F4-4BA5-AEB9-55348661C7BA@gmx.de> (raw)
In-Reply-To: <alpine.DEB.2.02.1506241233560.9487@uplift.swm.pp.se>
Hi Mikael,
thanks a lot.
On Jun 24, 2015, at 13:31 , Mikael Abrahamsson <swmike@swm.pp.se> wrote:
> On Tue, 23 Jun 2015, Sebastian Moeller wrote:
>
>> As Dave said it would be nice see RRUL data from the same testbed. It would be so nice if flint had a way to send different sized TCP packets… (I guess this might be faked with MSS clamping in the router and relaying on path MTU discovery?)
>
> What kind of tests should I run? I have rrul results now, both at the same time as running iperf3.
This is interesting. I also like the way iperf3 reports retransmits (BTW way how does it know this, I thought the kernel does the retransmits under the hood out of sight of applications). Since RRUL does not have such a nice report as iperf3 I will not be able to calculate the difference to the theoretical maximum transfer rates (also I lack insight on the ACK traffic).
> I set iperf3 to run with 10 parallel streams, different MSS per test, and let it run for 30 seconds into the rrul test.
The plots are interesting, even though I have a hard time with the logarithmic scale.
> So in all the tests, iperf3 session stops running half way into the rrul test.
I like how the RRUL flows soak up the newly available bandwidth.
>
> I set sqm to 500M up and down on eth0, ECN up and down, and not to squash DSCP in any direction.
I will have a look at the flint files, but it looks like the 1200ac does 500Mbps bidirectionally with SQM, so this looks like a decent machine for the present and (near?) future. Now I just need to wait until prices come down a tad (I hope that the 1900AC v2 release should drop the 1200ac’s process a bit).
Thanks for the tests, now I know what router to try next (the edgerouterX, which I had eyed as a replacement for the shaper in the wndr3700 tops out at 130K packets per second and hence will not really work that well for a 100/40 Mbps link).
Best Regards
Sebastian
>
> http://swm.pp.se/aqm/rrul-wrt1200ac-150624.pdf
>
> Tell me if there is more information I can provide or tests to run.
>
> --
> Mikael Abrahamsson email: swmike@swm.pp.se
next prev parent reply other threads:[~2015-06-26 9:46 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-19 14:44 [Cerowrt-devel] Latest build test - new sqm-scripts seem to work; "cake overhead 40" didn't Alan Jenkins
2015-06-19 16:41 ` Sebastian Moeller
2015-06-19 17:35 ` Alan Jenkins
2015-06-19 20:12 ` Dave Taht
2015-06-19 20:40 ` Alan Jenkins
2015-06-19 20:51 ` Dave Taht
2015-06-19 20:57 ` Dave Taht
2015-06-19 20:57 ` Alan Jenkins
2015-06-19 21:06 ` Dave Taht
2015-06-19 21:24 ` Dave Taht
2015-06-19 21:52 ` Luis E. Garcia
2015-06-19 23:32 ` Dave Taht
2015-06-20 5:52 ` Sebastian Moeller
2015-06-23 2:41 ` Jim Reisert AD1C
2015-06-23 7:20 ` Sebastian Moeller
2015-06-23 12:55 ` [Cerowrt-devel] performance numbers from WRT1200AC (Re: Latest build test - new sqm-scripts seem to work; "cake overhead 40" didn't) Mikael Abrahamsson
2015-06-23 14:09 ` Dave Taht
2015-06-23 17:25 ` Sebastian Moeller
2015-06-23 18:15 ` Jonathan Morton
2015-06-24 5:21 ` Mikael Abrahamsson
2015-06-24 5:19 ` Mikael Abrahamsson
2015-06-24 11:31 ` Mikael Abrahamsson
2015-06-24 16:32 ` Dave Taht
2015-06-25 1:53 ` Aaron Wood
2015-06-25 3:07 ` Mikael Abrahamsson
2015-06-25 3:32 ` Aaron Wood
2015-06-25 9:12 ` Mikael Abrahamsson
2015-06-25 10:26 ` Mikael Abrahamsson
2015-06-25 20:13 ` Dave Taht
2015-06-25 20:16 ` Dave Taht
2015-06-25 20:24 ` Toke Høiland-Jørgensen
2015-06-25 22:14 ` Dave Taht
2015-06-26 6:58 ` Mikael Abrahamsson
2015-06-26 7:12 ` Mikael Abrahamsson
2015-06-26 9:46 ` Sebastian Moeller [this message]
2015-06-26 12:26 ` Mikael Abrahamsson
2015-06-26 14:17 ` Sebastian Moeller
2015-06-26 14:49 ` Mikael Abrahamsson
2015-06-26 16:18 ` Jonathan Morton
2015-06-26 16:31 ` Mikael Abrahamsson
2015-06-26 16:35 ` Jonathan Morton
2015-06-26 17:04 ` Dave Taht
2015-06-26 18:24 ` Dave Taht
2015-06-26 18:38 ` Mikael Abrahamsson
2015-06-26 18:58 ` Dave Taht
2015-06-26 18:59 ` Dave Taht
2015-06-26 19:11 ` Mikael Abrahamsson
2015-06-26 19:13 ` Dave Taht
2015-06-27 5:03 ` Mikael Abrahamsson
2015-06-27 5:18 ` Dave Taht
2015-06-27 5:50 ` Mikael Abrahamsson
2015-06-27 17:59 ` Dave Taht
2015-06-27 18:23 ` Mikael Abrahamsson
2015-06-27 18:52 ` Dave Taht
2015-06-27 23:13 ` Sebastian Moeller
2015-06-28 7:06 ` Mikael Abrahamsson
2015-06-28 8:23 ` Sebastian Moeller
2015-06-28 10:29 ` Mikael Abrahamsson
2015-06-28 17:04 ` Sebastian Moeller
2015-06-28 17:32 ` Mikael Abrahamsson
2015-06-28 17:58 ` Jonathan Morton
2015-06-28 18:04 ` Dave Taht
2015-06-28 18:55 ` Sebastian Moeller
2015-06-28 19:17 ` Mikael Abrahamsson
2015-06-28 19:24 ` Sebastian Moeller
2015-06-28 20:48 ` Mikael Abrahamsson
2015-06-28 21:23 ` Sebastian Moeller
2015-06-29 4:58 ` Mikael Abrahamsson
2015-06-29 5:11 ` Mikael Abrahamsson
2015-06-29 7:46 ` Sebastian Moeller
2015-06-29 7:54 ` Mikael Abrahamsson
2015-06-29 7:56 ` Sebastian Moeller
2015-06-29 8:10 ` Sebastian Moeller
2015-06-29 8:17 ` Mikael Abrahamsson
2015-06-29 8:24 ` Sebastian Moeller
2015-06-29 7:44 ` Sebastian Moeller
2015-06-29 8:09 ` Mikael Abrahamsson
2015-06-29 8:34 ` Sebastian Moeller
2015-06-29 8:42 ` Sebastian Moeller
2015-06-29 9:12 ` Mikael Abrahamsson
2015-06-29 10:09 ` Toke Høiland-Jørgensen
2015-06-29 13:00 ` Mikael Abrahamsson
2015-06-29 13:34 ` Sebastian Moeller
2015-06-29 13:46 ` dpreed
2015-06-29 16:45 ` Jonathan Morton
2015-06-30 13:58 ` [Cerowrt-devel] Build instructions for regular OpenWRT with Ceropackages Mikael Abrahamsson
2015-06-30 16:20 ` dpreed
2015-06-30 19:58 ` Mikael Abrahamsson
2015-07-01 8:23 ` David Lang
2015-07-01 10:32 ` Mikael Abrahamsson
2015-07-01 11:55 ` Sebastian Moeller
2015-07-01 15:37 ` dpreed
2015-06-29 13:42 ` [Cerowrt-devel] performance numbers from WRT1200AC (Re: Latest build test - new sqm-scripts seem to work; "cake overhead 40" didn't) Sebastian Moeller
2015-06-29 16:44 ` Dave Taht
2015-06-29 18:24 ` Sebastian Moeller
2015-06-29 22:15 ` Mikael Abrahamsson
2015-06-29 22:49 ` Mikael Abrahamsson
2015-06-30 8:00 ` Mikael Abrahamsson
2015-06-30 9:40 ` Mikael Abrahamsson
2015-07-02 15:33 ` Mikael Abrahamsson
2015-07-02 15:39 ` Toke Høiland-Jørgensen
2015-07-02 15:43 ` Mikael Abrahamsson
2015-07-02 15:47 ` Toke Høiland-Jørgensen
2015-07-02 16:06 ` dpreed
2015-07-02 19:12 ` Mikael Abrahamsson
2015-07-07 1:07 ` David Lang
2015-07-02 16:09 ` Rich Brown
2015-07-02 16:12 ` Toke Høiland-Jørgensen
2015-07-03 11:38 ` Mikael Abrahamsson
2015-06-29 6:12 ` Mikael Abrahamsson
2015-06-28 18:48 ` Sebastian Moeller
2015-06-26 16:34 ` Dave Taht
2015-06-26 16:27 ` Sebastian Moeller
2015-06-26 16:36 ` Mikael Abrahamsson
2015-06-26 16:43 ` Dave Taht
2015-06-26 17:01 ` Mikael Abrahamsson
2015-06-23 14:35 ` [Cerowrt-devel] Latest build test - new sqm-scripts seem to work; "cake overhead 40" didn't Jim Reisert AD1C
2015-06-23 14:40 ` Dave Taht
2015-06-19 20:37 ` Sebastian Moeller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://lists.bufferbloat.net/postorius/lists/cerowrt-devel.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=43D5C3CE-F1F4-4BA5-AEB9-55348661C7BA@gmx.de \
--to=moeller0@gmx.de \
--cc=cerowrt-devel@lists.bufferbloat.net \
--cc=swmike@swm.pp.se \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox