[OpenWrt-Devel] [RFC PATCH] packages: Smart Queue Management for AQM Packet Scheduling and Qos from CeroWrt

[Sebastian Moeller]

Hello Stephan,


On Oct 9, 2014, at 01:01 , Stephan Günther <steph.guenther at gmail.com> wrote:

> Hi,
> 
> On Wed, Oct 8, 2014 at 10:10 PM, Hannu Nyman <hannu.nyman at iki.fi> wrote:
>> Dave Taht wrote on Thu Oct 2 03:49:15 CEST 2014:
>>> So I don't know where to go. Certainly I'd like to see the battle hardened
>>> sqm scripts (which are more flexible than the C code above) get more widely
>>> used and in BB.
>> 
>> SQM seems to work ok with the current Chaos Calmer trunk.
> 
> Works for mee too, and performs much better than the old luci-app-qos.
> I would love to see this as part of OpenWrt.
> 
> I did some RRUL test using netperf-wrapper on my ADSL 15/1Mbps PPPoE
> link and it looks good in the graphs. I also have an 6in4 tunnel
> inside PPPoE and IIRC fq_codel should detect these ipv6 flows. RRUL
> looks good at IPv6. Had this running at home for some days now, with
> moderate traffic and no issues so far.
> 
> But I was wondering which interface to select luci-app-sqm, as no
> tunnel intefaces are shown here. So i used the ethernet interface
> instead of the PPPoE link. Is this fine?

	So with using the ethernet link I see that the classification on egress does not seem to work anymore (and I loose some uplink bandwidth) but latency under load stays reasonable (all tested with netperf-wrapper’s RRUL test), Using pppoe-ge00 (I changed luci-app-sqm to show all devices except lo) I also notice the issue that this device can go away temporarily (while renegotiating the connection with the BRAS I assume) and that can lead to a half-baked SQM system where either the up or downlink (do not remember which, and test files are not accessible) ends up withe no shaping applied.
	Note that the kernel assumes different default per packet overheads for the ethernet interface (kernel automatically adds 14 bytes) and the pppoe-ethernet interface (where it looks like the kernel does not add any overhead), so I found on cerowrt I need to change the overhead number in SQM’s link layer tab to get similar results.
	I think shaping on the ethernet interface is what we should do (and try to figure out why classification does not seem to work)

> Minutes ago, I did a quick
> test and applied SQM to the PPPoE link by fixing luci-base to return
> also the virtual interfaces in net:get_interfaces(). But i didn't
> notice any difference or my test was too sloppy.

	Could you send me the json.gz file from both a run with SQM on the ethernet interfere and on the pppoe interface, please, so I can compare with my own tests?

Best Regards
	Sebastian

> 
> --
> Stephan
> _______________________________________________
> openwrt-devel mailing list
> openwrt-devel at lists.openwrt.org
> https://lists.openwrt.org/cgi-bin/mailman/listinfo/openwrt-devel
_______________________________________________
openwrt-devel mailing list
openwrt-devel at lists.openwrt.org
https://lists.openwrt.org/cgi-bin/mailman/listinfo/openwrt-devel