Development issues regarding the cerowrt test router project
 help / color / mirror / Atom feed
* [Cerowrt-devel] PIE and ADSL2+
@ 2013-11-20 10:08 Fred Stratton
  2013-11-22  9:10 ` Sebastian Moeller
  0 siblings, 1 reply; 4+ messages in thread
From: Fred Stratton @ 2013-11-20 10:08 UTC (permalink / raw)
  To: cerowrt-devel

I have been using PIE instead of fq_codel for approximately 10 days. It 
works well.

Should it?

Has PIE been optimized for ADSL?

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [Cerowrt-devel] PIE and ADSL2+
  2013-11-20 10:08 [Cerowrt-devel] PIE and ADSL2+ Fred Stratton
@ 2013-11-22  9:10 ` Sebastian Moeller
  2013-11-22  9:15   ` Fred Stratton
  0 siblings, 1 reply; 4+ messages in thread
From: Sebastian Moeller @ 2013-11-22  9:10 UTC (permalink / raw)
  To: Fred Stratton; +Cc: cerowrt-devel

Hi Fred,


On Nov 20, 2013, at 11:08 , Fred Stratton <fredstratton@imap.cc> wrote:

> I have been using PIE instead of fq_codel for approximately 10 days. It works well.

	Intrigued by your report I went ahead and tested simple.qos with fq_codel and pie (cerowrt 3.10.18-1) with rrul against  demo.tohojo.dk:
 /netperf-wrapper -l 300 -H demo.tohojo.dk rrul -p all_scaled -t my_silly_name

	Pie (with the default target of 20ms(?) shows around 120 ms ping delay (fq_codel shows 45ms) also the average downlink with fq_codel is roughly 10% higher than with pie. So at least in that test fq_codel seems better than pie. That said, compared to ping latencies up to 300ms (my primary router somehow restricts ;agencies to roughly 300ms)  with no AQM, just rate shaping with HTB, pie still keeps the internet more useable.
	
> 
> Should it?

	I think its designers wanted it to be a competent disc, so I guess it should :)

> 
> Has PIE been optimized for ADSL?

Best Regards
	Sebastian
> _______________________________________________
> Cerowrt-devel mailing list
> Cerowrt-devel@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cerowrt-devel


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [Cerowrt-devel] PIE and ADSL2+
  2013-11-22  9:10 ` Sebastian Moeller
@ 2013-11-22  9:15   ` Fred Stratton
       [not found]     ` <B9035D41-ACD6-4A8F-9878-8D345F5E248D@gmx.de>
  0 siblings, 1 reply; 4+ messages in thread
From: Fred Stratton @ 2013-11-22  9:15 UTC (permalink / raw)
  To: Sebastian Moeller, cerowrt-devel

Thank you.

Are you still using ADSL2+, Sebastian, or have you moved to fibre?


On 22/11/13 09:10, Sebastian Moeller wrote:
> Hi Fred,
>
>
> On Nov 20, 2013, at 11:08 , Fred Stratton <fredstratton@imap.cc> wrote:
>
>> I have been using PIE instead of fq_codel for approximately 10 days. It works well.
> 	Intrigued by your report I went ahead and tested simple.qos with fq_codel and pie (cerowrt 3.10.18-1) with rrul against  demo.tohojo.dk:
>   /netperf-wrapper -l 300 -H demo.tohojo.dk rrul -p all_scaled -t my_silly_name
>
> 	Pie (with the default target of 20ms(?) shows around 120 ms ping delay (fq_codel shows 45ms) also the average downlink with fq_codel is roughly 10% higher than with pie. So at least in that test fq_codel seems better than pie. That said, compared to ping latencies up to 300ms (my primary router somehow restricts ;agencies to roughly 300ms)  with no AQM, just rate shaping with HTB, pie still keeps the internet more useable.
> 	
>> Should it?
> 	I think its designers wanted it to be a competent disc, so I guess it should :)
>
>> Has PIE been optimized for ADSL?
> Best Regards
> 	Sebastian
>> _______________________________________________
>> Cerowrt-devel mailing list
>> Cerowrt-devel@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/cerowrt-devel


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [Cerowrt-devel] PIE and ADSL2+
       [not found]     ` <B9035D41-ACD6-4A8F-9878-8D345F5E248D@gmx.de>
@ 2013-11-22  9:31       ` Fred Stratton
  0 siblings, 0 replies; 4+ messages in thread
From: Fred Stratton @ 2013-11-22  9:31 UTC (permalink / raw)
  To: Sebastian Moeller, cerowrt-devel

Yes, PIE does apparently work better here than fq_codel. This is a 
subjective judgement. I have stopped using RRUL.



On 22/11/13 09:23, Sebastian Moeller wrote:
> Hi Fred,
>
>
> On Nov 22, 2013, at 10:15 , Fred Stratton <fredstratton@imap.cc> wrote:
>
>> Thank you.
>>
>> Are you still using ADSL2+, Sebastian, or have you moved to fibre?
> 	Yes, I am still on ADSL2+ (16M downlink 2.5M uplink); I hope to switch to VDSL2 soon (50M down, 10M up), since real fiber is not offered where I live. For completeness I have shaped down and up link to 95% of the raw link-rate, and use simple qos, with tc_stab, link layer ADSL, overhead 40, and that seems to work well in my setup. My link is quite robust, that is I get a number of FECs but only few CRCs (and FECs do not require retransmission of cells and thus do not impact the effective link speed).
> 	I have one question, does PIE work better for you than fq_codel on your test load (i think you try to watch some videos while up- and downloading is ongoing)?
>
> best
> 	Sebastian
>
>>
>> On 22/11/13 09:10, Sebastian Moeller wrote:
>>> Hi Fred,
>>>
>>>
>>> On Nov 20, 2013, at 11:08 , Fred Stratton <fredstratton@imap.cc> wrote:
>>>
>>>> I have been using PIE instead of fq_codel for approximately 10 days. It works well.
>>> 	Intrigued by your report I went ahead and tested simple.qos with fq_codel and pie (cerowrt 3.10.18-1) with rrul against  demo.tohojo.dk:
>>>   /netperf-wrapper -l 300 -H demo.tohojo.dk rrul -p all_scaled -t my_silly_name
>>>
>>> 	Pie (with the default target of 20ms(?) shows around 120 ms ping delay (fq_codel shows 45ms) also the average downlink with fq_codel is roughly 10% higher than with pie. So at least in that test fq_codel seems better than pie. That said, compared to ping latencies up to 300ms (my primary router somehow restricts ;agencies to roughly 300ms)  with no AQM, just rate shaping with HTB, pie still keeps the internet more useable.
>>> 	
>>>> Should it?
>>> 	I think its designers wanted it to be a competent disc, so I guess it should :)
>>>
>>>> Has PIE been optimized for ADSL?
>>> Best Regards
>>> 	Sebastian
>>>> _______________________________________________
>>>> Cerowrt-devel mailing list
>>>> Cerowrt-devel@lists.bufferbloat.net
>>>> https://lists.bufferbloat.net/listinfo/cerowrt-devel


^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2013-11-22  9:31 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-11-20 10:08 [Cerowrt-devel] PIE and ADSL2+ Fred Stratton
2013-11-22  9:10 ` Sebastian Moeller
2013-11-22  9:15   ` Fred Stratton
     [not found]     ` <B9035D41-ACD6-4A8F-9878-8D345F5E248D@gmx.de>
2013-11-22  9:31       ` Fred Stratton

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox